In-plant optimization operation method based on equivalent unit

Abstract

The invention discloses an in-plant optimization operation method based on an equivalent unit, and belongs to the technical field of hydroelectric energy dispatching. According to the method, firstly, under the given water head discrete precision and flow discrete precision, discrete flow under different water heads is calculated through dynamic planning, and the optimal flow table and the optimal output table of an equivalent unit under the available unit number are determined; distributing unit flow among the equivalent units through IQPSO (Inter-Quality Particle Swarm Optimization); and finally, calculating the output under the specific flow distribution scheme according to the optimal flow table and the optimal output table of the equivalent unit. According to the in-plant optimization operation method based on the equivalent unit, rapid solution from the short-term scheduling boundary to the in-plant optimization operation result is realized.

Description

Technical Field

[0001] The present application belongs to the technical field of hydropower energy dispatching, and more specifically, to an in-plant optimization operation method based on equivalent units. Background Art

[0002] my country's energy system is gradually transitioning from fossil energy to a clean energy system dominated by renewable energy. Hydropower has the advantages of being pollution-free and renewable, and is considered "high-quality electricity". In addition, hydropower units have the characteristics of rapid start and stop, fast response speed, and fast load climbing, and play a vital role in maintaining the stability of the power grid load.

[0003] The optimization operation in the plant mainly considers various complex constraints such as the power grid, power station, and units under the condition that the total load or total power generation flow of the hydropower station is given, and determines the final optimal operation mode in the plant, including the optimal number of participating generators, unit combination, and load distribution between units, so as to improve the efficiency of the power station. From the perspective of scheduling application scenarios, the optimization operation in the plant is divided into "determining water by electricity" and "determining electricity by water", and the optimization purpose and constraint conditions are different. The optimization problem in the plant involves complex constraints on unit variables. Some studies construct models by simplifying or relaxing constraints, which cannot accurately describe the problems faced by the units, and the results obtained may not be practically applicable; some studies consider constraints more comprehensively, but the models are complex and the model solving efficiency is not high. In addition, some studies have studied the problem of coupling calculation between plant optimization and short-term scheduling models, but they have not been extended to the basin cascade level, and the calculation logic is relatively complex. Therefore, it is urgent to explore an in-plant optimization method that can accurately describe practical problems and has high applicability. Summary of the invention

[0004] In response to the above defects or improvement needs of the prior art, the present application provides an in-plant optimization operation method based on equivalent units, which aims to solve the technical problem that the existing in-plant optimization methods are inefficient due to the complex constraints of unit variables.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for optimizing operation of an equivalent unit within a plant, which specifically includes the following steps:

[0006] S1. Under given water head discrete accuracy and flow discrete accuracy, the discrete flow under different water heads is calculated by dynamic programming to determine the optimal flow table and optimal output table of equivalent units under the number of available units;

[0007] S2, allocate unit flow between equivalent units through IQPSO;

[0008] S3. Derivation of the output under a specific flow distribution scheme based on the optimal flow table and optimal output table of the equivalent unit.

[0009] Preferably, the step S2 specifically includes the following sub-steps:

[0010] S21. Consider a solution for the flow distribution between equivalent units as individual x of the population. i , create the initial population R t , t = 1;

[0011] S22, using the current unit status as a constraint processing strategy, t Make constraint corrections;

[0012] S23, yes Calculate individual x i The fitness f i , update individual x i The optimal fitness f i * With the optimal position p i ;

[0013] S24, update individual positions, thereby generating a new group R t+1 ;

[0014] S25, using the current unit status as a constraint processing strategy, t+1 Make constraint corrections;

[0015] S26, let t = t + 1, if t > T, then according to population R t Individual x in i The value of is used to allocate the flow between equivalent units; otherwise, go to step S23.

[0016] Preferably, the current unit state is used as a constraint processing strategy to perform constraint correction on the population, specifically:

[0017] S211, if the population is the initial population, proceed to step S212; otherwise, proceed to step S214;

[0018] S212, traverse the current unit status, set the shutdown unit to {o1, o2, ...o l}, the power generation flow in the current period is Q t ;

[0019] S213, yes So that x i，o =0,o∈{o1,o2,…o l}; where R1 is the initial population;

[0020] S214, let i=1;

[0021] S215, Calculation Among them, x i，jrepresents the flow rate of the jth unit of the i-th individual in the population; L is the number of units in the equivalent unit;

[0022] S216, update individual,

[0023] S217, i=i+1, if i>N, then complete the constraint correction of the population; otherwise, go to step S215, where N is the number of individuals in the population.

[0024] Preferably, updating the individual position in step S24 is specifically as follows:

[0025]

[0026] in, is the individual x at time t+1 i , is the individual x at time t i , D i is the local attractor, α is the expansion coefficient, mbest is the average optimal position, and u is a random number uniformly distributed between 0 and 1.

[0027] Preferably, the local attractor D i Specifically:

[0028] D i =ψp i +(1-ψ)g

[0029] Among them, ψ is a random number uniformly distributed between 0 and 1; g is the global optimal position.

[0030] Preferably, the expansion coefficient α is specifically:

[0031] α=max{α f , α t}

[0032]

[0033] Among them, C, C1, C2 are constants; T is the total number of iterations; t is the current number of iterations; f max is the fitness f i The maximum value among min is the fitness f i The minimum value among f , α t} means to find α f and α t The maximum value in .

[0034] Preferably, the average optimal position mbest is specifically:

[0035]

[0036]

[0037] Among them, mbest j is the average position of the jth dimension of mbest, L is the number of units in the equivalent unit, x i，j It represents the flow rate of the i-th unit of the i-th individual in the population; N is the number of individuals in the population.

[0038] Preferably, the step S3 specifically includes the following sub-steps:

[0039] S31, input water head H, equivalent unit flow distribution scheme Q = {Q1, Q2, ..., Q l}, where l is the number of equivalent units divided into power stations;

[0040] S32, calculate the output range of a single unit under the current type by type, and convert the output constraint into a flow constraint, and then calculate the minimum number of units of the current i-th equivalent unit and the maximum number of units Set the flow range of the current equivalent unit i

[0041] S33, calculate the current maximum power station output N max and flow range [Q min , Q max ];

[0042] S34. If sum(Q)>Q max And meet Then mark the constraint violation, let {=ζ+1, Go to step S33; otherwise terminate the calculation and output N max , sum(Q)-Q max For discarding water;

[0043] If sum(Q) min And meet but Go to step S33; otherwise, terminate the calculation and mark the flow abnormality;

[0044] Among them, ζ is the number of constraint violations; num i is the number of units contained in the ith equivalent unit; sum(Q) is the sum of the set Q = {Q1, Q2, ..., Q l} and;

[0045] S35, set Q res is the flow to be adjusted, and the flow to be adjusted is calculated by each equivalent unit; let o = {o1, o2, ... l} indicates that the unit has been turned on. and​ are the lower and upper limits of the flow rate of unit j in o, respectively. Perform the following calculations:

[0046] Q res =Q res +Δ j

[0047]

[0048] Among them, Q j is the flow rate of unit j in o; min(,) is the minimum value function;

[0049] S36, adjust the equivalent unit flow:

[0050] set up Indicates the regulating capacity of unit j, which is calculated from the upper and lower limits of the unit. If it is greater than 0, it means an increase; otherwise, it means a decrease. Set o = {o1, o2, ...o l}according to Sort in ascending order;

[0051] Let j = 1, and increase j gradually. If there exists Then the unit is adjusted on average, Where j≤q≤l; otherwise, adjust the flow to the boundary value in ascending order of regulation capacity and update Q res , until Q res is 0; where Q q represents the power generation flow of the qth equivalent unit;

[0052] S37. According to the current water head H and the equivalent unit flow distribution plan Q, interpolation calculation is performed on the prepared optimal flow distribution table and optimal output table for each equivalent unit, and the sum is used as the optimal output of the power station to obtain the flow distribution plan within the equivalent unit.

[0053] In a second aspect, the present application provides an electronic device, comprising: a memory for storing programs; a processor for executing the programs stored in the memory, when the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0054] In a third aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0055] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0056] This application uses dynamic programming to prepare the optimal flow table and optimal output table of equivalent units in advance. After determining the number of available units in the equivalent unit, IQSPO can be used to optimize the flow allocation of the equivalent unit, thereby solving the defects of complex short-term scheduling model of the unit, high calculation complexity and low solution efficiency, and realizing the rapid solution from short-term scheduling boundary to the optimal operation results within the plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the in-plant optimization operation method provided in the embodiment of the present application.

[0058] Figure 2 It is a schematic diagram of the start-up and shutdown plan of the D1 unit in the peak-shaving scenario provided in an embodiment of the present application.

[0059] Figure 3 It is a schematic diagram of the start-up and shutdown plan of the D2 unit in the peak-shaving scenario provided in an embodiment of the present application.

[0060] Figure 4 It is a schematic diagram of the start-up and shutdown plan of the D1 unit in a non-peak-shaving scenario provided in an embodiment of the present application.

[0061] Figure 5 It is a schematic diagram of the start-up and shutdown plan of the D2 unit in a non-peak-shaving scenario provided in an embodiment of the present application.

[0062] Figure 6 It is a result schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0065] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0066] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

[0067] First, the technical terms involved in the embodiments of the present application are introduced.

[0068] DP (Dynamic Programming) is a method used in the fields of mathematics, management science, computer science, economics and bioinformatics to solve complex problems by decomposing the original problem into relatively simple sub-problems. Next, the technical solution provided in the embodiment of the present application is introduced.

[0069] IQP SO (Improved Quantum-behaved Particle Swarm Optimization) is an optimization algorithm that is improved by combining the quantum-behaved particle swarm optimization (QPSO) algorithm with the concept of adversarial learning.

[0070] Then, the technical solution of the present application is further described by examples. Figure 1 The flowchart of an in-plant optimization operation method based on an equivalent unit is shown, which includes the following steps:

[0071] S1. Under given water head discrete accuracy and flow discrete accuracy, the discrete flow under different water heads is calculated through dynamic programming to determine the optimal flow table and optimal output table of the equivalent unit under the available number of units.

[0072] S2. Allocate unit flow between equivalent units through IQPSO; specifically, it includes the following sub-steps:

[0073] S21. Consider a solution for the flow distribution between equivalent units as individual x of the population. i , create the initial population R t , t=1; and set the initial parameters at the same time.

[0074] S22, using the current unit status as a constraint processing strategy, t Make constraint corrections.

[0075] S23, yes Calculate individual x i The fitness f i , update individual x i The optimal fitness f i * With the optimal position p i; Calculate the global optimal fitness Update the global optimal position g; calculate the local attractor D i :

[0076] D i =ψp i +(1-ψ)g

[0077] Among them, ψ is a random number uniformly distributed between 0 and 1; g is the global optimal position.

[0078] Calculate the mean optimal position mbest:

[0079]

[0080]

[0081] Among them, mbest j is the average position of the jth dimension of mbest, L is the number of units in the equivalent unit, x i,j Represents the flow rate of the jth unit of the i-th individual in the population; N is the number of individuals in the population.

[0082] Calculate the expansion coefficient α:

[0083] α=max{α f , α t}

[0084]

[0085] Among them, C, C1, C2 are constants; T is the total number of iterations; t is the current number of iterations; f max is the fitness f i The maximum value among min is the fitness f i The minimum value among f , α t} means to find α f and α t The maximum value in .

[0086] S24, update individual positions, thereby generating a new group R t+1 ;

[0087] Update individual positions specifically as follows:

[0088]

[0089] in, is the individual x at time t+1 i , is the individual x at time t i , D iis the local attractor, α is the expansion coefficient, mbest is the average optimal position, and u is a random number uniformly distributed between 0 and 1.

[0090] S25, using the current unit status as a constraint processing strategy, t+1 Make constraint corrections;

[0091] S26, let t = t + 1, if t > T, then according to population R t Individual x in i The value of is used to allocate the flow between equivalent units; otherwise, go to step S23.

[0092] Among them, the current unit state is used as a constraint processing strategy to perform constraint correction on the population, specifically:

[0093] S211, if the population is the initial population, proceed to step S212; otherwise, proceed to step S214;

[0094] S212, traverse the current unit status, set all the shut-down units to {o1, o2, ...o l}, the power generation flow in the current period is Q t ;

[0095] S213, yes So that x i，o =0,o∈{o1,o2,…o l}; where R1 is the initial population;

[0096] S214, let i=1;

[0097] S215, Calculation Among them, x i，j represents the flow rate of the jth unit of the i-th individual in the population; L is the number of units in the equivalent unit;

[0098] S216, update individual,

[0099] S217, i=i+1, if i>N, then complete the constraint correction of the population; otherwise, go to step S215, where N is the number of individuals in the population.

[0100] S3, calculating the output under a specific flow distribution scheme according to the optimal flow table and the optimal output table of the equivalent unit, step S3 specifically includes the following sub-steps:

[0101] S31, input water head H, equivalent unit flow distribution scheme Q = {Q1, Q2, ..., Q l}, where l is the number of equivalent units divided into power stations;

[0102] S32, calculate the output range of a single unit under the current type by type, and convert the output constraint into a flow constraint, and then calculate the minimum number of units of the current i-th equivalent unit and the maximum number of units Set the flow range of the current equivalent unit i

[0103] S33, calculate the current maximum power station output N max and flow range [Q min , Q max ];

[0104] S34. If sum(Q)>Q max And meet Then mark the constraint violation, let {=ζ+1, Go to step S33; otherwise terminate the calculation and output N max ,sum(Q)-Q max For discarding water;

[0105] If sum(Q) min And meet but Go to step S33; otherwise, terminate the calculation and mark the flow abnormality;

[0106] Among them, ζ is the number of constraint violations; num i is the number of units contained in the ith equivalent unit; sum(Q) is the sum of the set Q = {Q1, Q2, ..., Q l} and;

[0107] S35, set Q res is the flow to be adjusted, and the flow to be adjusted is calculated by each equivalent unit; let o = {o1, o2, ... l} indicates that the unit has been turned on. and are the lower and upper limits of the flow rate of unit j in o, respectively. Perform the following calculations:

[0108] Q res =Q res +Δ j

[0109]

[0110] Among them, Q j is the flow rate of unit j in o; mmin(,) is the minimum value function;

[0111] S36, adjust the equivalent unit flow:

[0112] set up ​Indicates the regulating capacity of unit j, which is calculated from the upper and lower limits of the unit. If it is greater than 0, it means an increase; otherwise, it means a decrease. Set o = {o1, o2, ...o l}according to Sort in ascending order;

[0113] Let j = 1, and increase j gradually. If there exists Then the unit is adjusted on average, Where j≤q≤l; otherwise, adjust the flow to the boundary value in ascending order of regulation capacity and update Q res , until Q res is 0; where Q q represents the power generation flow of the qth equivalent unit;

[0114] S37. According to the current water head H and the equivalent unit flow distribution plan Q, interpolation calculation is performed on the prepared optimal flow distribution table and optimal output table for each equivalent unit, and the sum is used as the optimal output of the power station to obtain the flow distribution plan within the equivalent unit.

[0115] Finally, the above results are returned.

[0116] In order to verify the effect of the model method proposed in this invention, a hydropower station in the Yangtze River Basin was selected as the research object, and the key problems of unit combination and unit load distribution under given water level boundaries were analyzed, modeled and solved.

[0117] The model aims to maximize the power station output during the dispatch period, and the objective function is expressed as follows:

[0118]

[0119] Where LmaxN(·) is the approximate maximum function; H = (H1, H2, …, H T ) period; Q = (Q1, Q2, ..., Q T ) is the power generation flow in a given period; T is the total dispatch period; l is the equivalent unit number summarized from the perspective of the power station, and L is the total number of equivalent units; f(·) is the equivalent unit output function, which is solved by the dynamic programming model DP; and Ql,t are the net water head and power generation flow of the equivalent unit in period t respectively.

[0120] During daily operation, the hydropower station needs to perform peak-shaving and frequency-regulating operations according to the power grid. The daily peak-shaving process can be divided into single-peak and double-peak conditions. Among them, the single-peak condition can be regarded as a simplified case of the double-peak condition. In order to verify the applicability of the model under different conditions, the study selected non-peak-shaving periods and double-peak periods for model testing. The above-mentioned model was used to study the scenario, and the traditional unit flow distribution model and the model based on the equivalent unit in this application were recorded as D1 and D2, respectively.

[0121] On November 14, the maximum output was 14.5337 million kW, and the minimum output was 8.5227 million kW. The output difference was 6.011 million kW, and the double-peak characteristics were obvious. It was used as the No. 1 test scenario to verify the performance of the model under double-peak regulation; on December 21, the maximum output was 7.4491 million kW, and the minimum output was 6.55145 million kW. The daily output change was small, so it was used as the No. 2 scenario to verify the model performance under smooth scheduling. The detailed data are shown in Table 1:

[0122] Table 1

[0123]

[0124] In the bi-peak dispatch scenario, the D1 and D2 models solve the unit start-up and shutdown plans as follows: Figure 2 and Figure 3 shown.

[0125] In order to compare the optimization of D1 and D2 and the operation of the units and analyze the stability of the calculation results, the number of unit changes during the scheduling period is statistically shown in Table 2:

[0126] Table 2

[0127]

[0128]

[0129] The load distribution results of D1 unit in the peak load regulation scenario are shown in Table 3:

[0130] Table 3

[0131]

[0132] The load distribution results of D2 unit in the peak load regulation scenario are shown in Table 4:

[0133] Table 4

[0134]

[0135]

[0136] From the perspective of the rationality and economy of the operation of the units in the plant, the calculation results of D1 and D2 are consistent with the actual output change trend, and are 2.444 million kWh and 2.522 million kWh higher than the actual power generation respectively; in the calculation results of D1 and D2, the units are operating in the high-efficiency operating range, ensuring the efficient use of water resources.

[0137] From the perspective of unit operation safety, both D1 and D2 can arrange the processing plan more appropriately to make the output fall within the stable area of ​​the unit and avoid unit oscillation.

[0138] From the perspective of stability and continuity, the number of units started during the time periods calculated by D1 and D2 is the same.

[0139] From the schematic diagram of the unit startup and shutdown plan, it can be clearly seen that the D2 solution result has better continuity in unit load distribution.

[0140] Combined with the number of start-up and shutdown times in each period, it was found that D1 and D2 had similar adjustment methods at the beginning of the scheduling period and the beginning of peak regulation. However, when the output decreased at the end of peak regulation, D1 experienced large-scale unit changes. The reason was that when the total power generation flow dropped significantly, the unit operating status of the previous period could not provide guidance for the later period. Combined with the objective function of maximizing the total output of the period, the model performed a large number of random searches, which caused a large number of unit changes in D1 during the random optimization. In comparison, D2 also had relatively good continuity in the stage of power generation flow decline. The reason was that there were multiple units within the equivalent unit that could replace each other, which largely avoided the large-scale load transfer caused by random optimization of the unit, making D2 show better continuity.

[0141] In addition to the peak-shaving situation, the hydropower station has a scheduling period with a small daily peak-shaving capacity (less than 1 million kW), which is marked as a non-peak-shaving scenario. The following study is conducted on the non-peak-shaving scenario. The D1 and D2 solution for the unit start-up and shutdown states in the non-peak-shaving scenario are plotted as follows: Figure 4 and Figure 5 shown.

[0142] Table 5 shows the statistics of the number of units in operation and the number of units changed during the dispatch period:

[0143] Table 5

[0144]

[0145] For a more comprehensive analysis, the load distribution results of D1 unit in the non-peak load regulation scenario are shown in Table 6:

[0146] Table 6

[0147]

[0148]

[0149] The load distribution results of D2 unit in the non-peak load regulation scenario are shown in Table 7:

[0150] Table 7

[0151]

[0152] In the non-peak-shaving scenario, the overall load change during the dispatch period is small, but there are still small-scale load increases and decreases. As can be seen from the table, except for D1, which has more unit changes during the output reduction stage, the output units of D1 and D2 show good stability in the remaining periods, and there is no frequent load transfer between units. Overall, when facing the situation of reduced power flow, D1 still has the phenomenon of multiple unit status changes. Observing the changed units, it is found that some units that are closed and opened in the same period belong to the same unit type in the equivalent unit concept. Due to the randomness of the D1 model solution, the replacement of units of the same type occurs, so there will be more unit changes during the flow reduction stage. In contrast, D2 can transition well from high power flow to low power flow stage, showing higher stability. From the perspective of safety and economy, the D1 and D2 models increase the actual power generation by 1.046 million kWh and 282,000 kWh respectively, which can meet the unit safety restrictions and increase the power generation efficiency.

[0153] Considering the solution efficiency of D1 and D2 in peak-shaving and non-peak-shaving scenarios, it is found that the solution speed of D2 is much faster than that of D1. The reason is that the output calculation of D2 needs to use the optimal flow table and optimal output table of equivalent units made in advance by dynamic programming. After determining the number of available units in the equivalent unit, IQSPO can be used to optimize the flow distribution of equivalent units. Under the premise of completing the above dynamic programming table, it belongs to a one-dimensional optimization problem with a fast optimization speed, but the optimal output table and the optimal flow table need to set the flow discrete accuracy in advance. The increase in discrete accuracy will increase the time consumption of making the optimal solution table. D1 belongs to a two-layer nested optimization problem, which requires IGA and IQPSO to run alternately, and the optimization takes a long time. From the results of the scheduling plan, both D1 and D2 can reasonably arrange the unit start-up and shutdown plans, meet the unit start-up and shutdown time requirements, and ensure that the units are in a high efficiency output range. Under the constraints of the branch plant, D1 and D2 can reasonably arrange the load between the branches, and there is no extreme branch output phenomenon. In addition, through the optimization calculation of D1 and D2, the power generation efficiency of the power station has been improved to varying degrees. From the perspective of the overall unit changes, the D2 solution has higher stability, can better handle the changes in power generation flow, and is more practical.

[0154] Based on the method in the above embodiment, the embodiment of the present application provides an electronic device, such as Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the method in the above embodiment.

[0155] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0156] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0157] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0158] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0159] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0160] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a storage medium or transmitted through the storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0161] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0162] The above content is easily understood by those skilled in the art. The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A plant optimization operation method based on equivalent units, characterized in that: The specific steps include: S1. Under given water head discrete accuracy and flow discrete accuracy, the discrete flow under different water heads is calculated by dynamic programming to determine the optimal flow table and optimal output table of equivalent units under the number of available units; S2, allocate unit flow between equivalent units through IQPSO; S3. Derivation of the output under a specific flow distribution scheme based on the optimal flow table and optimal output table of the equivalent unit.

2. The in-plant optimization operation method according to claim 1, characterized in that: The step S2 specifically includes the following sub-steps: S21. Consider a solution for the flow distribution between equivalent units as individual x of the population i , create the initial population R t ,t=1; S22, using the current unit status as a constraint processing strategy, t Make constraint corrections; S23, yes Calculate individual x i The fitness f i , update individual x i The optimal fitness f i * With the optimal position p i ; S24, update individual positions, thereby generating a new group R t+1 ; S25, using the current unit status as a constraint processing strategy, t+1 Make constraint corrections; S26, let t = t + 1, if t> T, then according to population R t Individual x in i The value of is used to allocate the flow between equivalent units; otherwise, go to step S23.

3. The in-plant optimization operation method according to claim 2, characterized in that: The current unit status is used as a constraint processing strategy to modify the population constraints, specifically: S211, if the population is the initial population, proceed to step S212; otherwise, proceed to step S214; S212, traverse the current unit status, set the shutdown unit to {o1, o2, ... o l }, the power generation flow in the current period is Q t ; S213, yes So that x i,o =0,o∈{o1,o2,…o l }; where R1 is the initial population; S214, let i=1; S215, Calculation Among them, x i,j represents the flow rate of the jth unit of the i-th individual in the population; L is the number of units in the equivalent unit; S216, update individual, S217, i=i+1, if i>N, then complete the constraint correction of the population; otherwise, go to step S215, where N is the number of individuals in the population.

4. The in-plant optimization operation method according to claim 2, characterized in that: The specific updating of individual positions in step S24 is as follows: in, is the individual x at time t+1 i , is the individual x at time t i , D i is the local attractor, α is the expansion coefficient, mbest is the average optimal position, and u is a random number uniformly distributed between 0 and 1.

5. The in-plant optimization operation method according to claim 4, characterized in that: Local attractor D i Specifically: D v =ψp i +(1-ψ)g Among them, ψ is a random number uniformly distributed between 0 and 1; g is the global optimal position.

6. The in-plant optimization operation method according to claim 4, characterized in that: The expansion coefficient α is specifically: α=max{α f ,a t } Among them, C, C1, C2 are constants; T is the total number of iterations; t is the current number of iterations; f max is the fitness f i The maximum value among min is the fitness f i The minimum value in max{α f ,α t } means to find α f and α t The maximum value in .

7. The in-plant optimization operation method according to claim 4, characterized in that: The average optimal position mbest is specifically: Among them, mbest j is the average position of the jth dimension of mbest, L is the number of units in the equivalent unit, x i,j Represents the flow rate of the jth unit of the i-th individual in the population; N is the number of individuals in the population.

8. The in-plant optimization operation method according to claim 1, characterized in that: The step S3 specifically includes the following sub-steps: S31, input water head H, equivalent unit flow distribution scheme Q = {Q1, Q2, ..., Q l }, where l is the number of equivalent units divided into power stations; S32, calculate the output range of a single unit under the current type by type, and convert the output constraint into a flow constraint, and then calculate the minimum number of units of the current i-th equivalent unit and the maximum number of units Set the flow range of the current equivalent unit i S33, calculate the current maximum power station output N max and flow range [Q min ,Q max ]; S34. If sum(Q)>Q max And meet Then mark the constraint violation, let ζ=ζ+1, Go to step S33; otherwise terminate the calculation and output N max , sum(Q)-Q max For discarding water; If sum(Q) min And meet but Go to step S33; otherwise, terminate the calculation and mark the flow abnormality;​ Among them, ζ is the number of constraint violations; num i is the number of units contained in the ith equivalent unit; sum(Q) is the sum of the set Q = {Q1, Q2, …, Q l } and; S35, set Q res is the flow to be adjusted, and the flow to be adjusted is calculated by each equivalent unit; let o = {o1, o2, ... l } indicates that the unit has been turned on. and are the lower and upper limits of the flow rate of unit j in o, respectively. Perform the following calculations: Q res =Q res +Δ j Among them, Q j is the flow rate of unit j in o; min(,) is the minimum value function; S36, adjust the equivalent unit flow: set up Indicates the regulating capacity of unit j, which is calculated from the upper and lower limits of the unit. If it is greater than 0, it means an increase; otherwise, it means a decrease. Set o = {o1, o2, ... l }according to Sort in ascending order; Let j = 1, and increase j gradually. If there exists Then the unit is adjusted on average, Where j≤q≤l; otherwise, adjust the flow to the boundary value in ascending order of regulation capacity and update Q res , until Q res is 0; where Q q represents the power generation flow of the qth equivalent unit; S37. According to the current water head H and the equivalent unit flow distribution plan Q, interpolation calculation is performed on the prepared optimal flow distribution table and optimal output table for each equivalent unit, and the sum is used as the optimal output of the power station to obtain the flow distribution plan within the equivalent unit.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the program stored in the memory. When the program stored in the memory is executed, the processor is configured to execute the method according to any one of claims 1 to 8.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

Images