Artificial intelligence-based power balance generator access scheme design optimization method

Abstract

The application provides an artificial intelligence-based power balance generator access scheme design optimization method, obtains an access scheme according to the type of a power balance generator and the access point of the power balance generator, searches for an extreme operation mode set under each access scheme based on a dichotomy search method, selects an access scheme with the lowest cost as the target if the extreme operation mode set under each access scheme is empty, optimizes parameters of an access scheme with a non-empty extreme operation mode set based on an improved particle swarm optimization algorithm, discards the access scheme if the extreme operation mode set searched based on the dichotomy search method under the access scheme after parameter optimization is still non-empty, and selects an access scheme with the lowest cost as the target if the extreme operation mode set of all access schemes is empty. The application realizes the selection of the most economical, reasonable and reliable power balance generator access power system scheme by searching for extreme operation modes under different power balance generator access schemes and optimizing the parameters of controllers such as exciter and governor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system dynamic security and stability analysis, in particular to a power balance generator access scheme design optimization method based on artificial intelligence. BACKGROUND

[0002] The statements in this section merely provide background technology related to the present application and do not necessarily constitute prior art.

[0003] For a double-reheat unit, the reheated steam temperature is high, and the use of a regenerative drive small steam turbine without a steam cooler can save costs, reduce initial investment, and improve the safety and reliability of the unit. The regenerative drive small steam turbine drives a 100% capacity boiler feed pump at one end and a power balance generator at the other end. The small steam turbine inlet flow is determined by the self-balancing extraction of the regenerative heater, and the feed pump output is determined by the feed water flow and the feed water pressure head under certain conditions, and the power balance needs to be achieved by adjusting the output of the small generator.

[0004] The inventor found that there are many power balance generator access schemes at present, and it is still not possible to select the optimal scheme, that is, it is not possible to effectively adaptively compare each access scheme, and it is not possible to select the most economical, reasonable and reliable power balance generator access power system scheme. SUMMARY

[0005] In order to solve the problems of the prior art, the present application provides a power balance generator access scheme design optimization method based on artificial intelligence, which realizes the selection of the most economical, reasonable and reliable power balance generator access power system scheme by searching for extreme operating modes under different power balance generator access schemes and optimizing the parameters of exciter, governor and other controllers.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] The present application provides a power balance generator access scheme design optimization method based on artificial intelligence.

[0008] A power balance generator access scheme design optimization method based on artificial intelligence includes the following processes:

[0009] An access scheme obtained according to the type of the power balance generator and the access point of the power balance generator is obtained;

[0010] An extreme operating mode set under each access scheme is searched based on the dichotomy search method;

[0011] If the extreme operation mode set of each access scheme is empty set, the access scheme selection is performed with the lowest cost as the target; otherwise, the parameter optimization is performed on the access scheme with the extreme operation mode set not empty set based on the improved particle swarm optimization algorithm;

[0012] If the extreme operation mode set searched based on the dichotomy search method under the access scheme after parameter optimization is still not empty set, the access scheme is discarded; otherwise, the access scheme with the extreme operation mode set empty set is selected with the lowest cost as the target.

[0013] Further, the access scheme includes:

[0014] The power balance synchronous generator access plant power system connection scheme, the power balance asynchronous generator access plant power system connection scheme, the power balance synchronous generator access generator outlet connection scheme, the power balance asynchronous generator access generator outlet connection scheme, the power balance synchronous motor access plant power system connection scheme, the power balance asynchronous motor access plant power system connection scheme, the power balance synchronous motor access generator outlet connection scheme, and the power balance asynchronous motor access generator outlet connection scheme.

[0015] Further, the extreme operation mode set under each access scheme is searched based on the dichotomy search method, including:

[0016] Suppose the value range of the active power P1 of the No. 1 side generator set is [P 1min ,P 1max ], the value range of the active power P2 of the No. 2 side large generator is [P 2min ,P 2max ], the active power P1 of the No. 1 side large generator set is taken as P 1min +jΔP1, and the cycle number j is set as 0;

[0017] For each small section [P 2,k ,P 2,k+1 ], P 2low =P 2,k and P 2high =P 2,k+1 are taken respectively, the transient voltage value of the node where the motor is located, the transient frequency value and the damping ratio of all nodes in the power plant are tested when the active power of the No. 1 side large generator and the active power of the No. 2 side large generator are equal to (P1, P 2low ) and (P1, P 2high ) respectively, and the cycle number k is set as 1;

[0018] According to the set voltage safety and stability criterion of the power system, the frequency safety and stability criterion of the power system, and the low-frequency oscillation stability criterion of the power system, it is judged that the power system is stable when the active power of the No. 1 side large generator and the active power of the No. 2 side large generator are equal to (P1, P 2low ) and (P1, P 2hightransient stability under the operating mode of (P1, P

[0019] If the system is transiently stable under the operating mode of (P1, P 2low ) and transiently unstable under the operating mode of (P1, P 2high ), there is no stable boundary point in the segment [P 2,k , P 2,k+1 ] and k = k + 1.

[0020] If k > n, j = j + 1.

[0021] If j > (P 1max - P 1min ) / ΔP1, the loop is ended and the result is outputted, and if j < (P 1max - P 1min ) / ΔP1, the next j loop is executed.

[0022] If k < n, the next k loop is executed.

[0023] If the system is transiently unstable under the operating mode of (P1, P 2low ) and transiently stable under the operating mode of (P1, P 2high ), P 2medium = (P 2low + P 2high ) / 2 is taken, and the loop number i = 1 is set.

[0024] If P 2medium - P 2low < 0.01, the stable boundary point of the system in the segment [P 2,k , P 2,k+1 ] is equal to P 2medium and k = k + 1.

[0025] If k > n, j = j + 1.

[0026] If j > (P 1max - P 1min ) / ΔP1, the loop is ended and the result is outputted, and if j < (P 1max - P 1min ) / ΔP1, the next j loop is executed.

[0027] If k < n, the next k loop is executed.

[0028] If P 2medium - P 2high > 0.01, the transient voltage value of the node where the motor is located, the transient frequency value and the damping ratio of all nodes in the power plant are tested when the output of the large generator on the No. 1 side and the output of the large generator on the No. 2 side are equal to (P1, P 2medium ).

[0029] According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system in the (P1, P 2medium ) operating mode is judged.

[0030] If the system is transiently unstable in the (P1, P 2medium ) operating mode, P 2low =P 2medium , if the system is transiently stable in the (P1, P 2medium ) operating mode, P 2high =P 2medium , and i=i+1.

[0031] The stable boundary points obtained by the above process are fitted to obtain the stable boundary under each access scheme, and then the extreme operating mode set under each access scheme is obtained.

[0032] Further, the power system voltage safety and stability criterion comprises that the voltage of the node where the motor is located is not lower than 0.8 per unit value in the transient process.

[0033] Further, the power system frequency safety and stability criterion comprises that the transient frequency of all nodes in the power plant is not lower than 49.9 Hz and not higher than 50.1 Hz.

[0034] Further, the power system low frequency oscillation stability criterion comprises that the damping ratio is lower than 0.04 for a weak damping system, 0.04-0.05 for a suitable damping system, and higher than 0.05 for a high damping ratio system.

[0035] Further, the particle swarm optimization algorithm comprises:

[0036] Initialize the particle swarm and set the related parameters;

[0037] Set the current iteration number t=1;

[0038] According to the minimum target function set by the extreme operating mode set searched under the current access scheme;

[0039] Calculate the fitness value of each particle;

[0040] Find the current individual optimal solution of each particle;

[0041] Find the current global optimal solution of the entire particle swarm;

[0042] Judge whether the convergence criterion is met, i.e. whether the iteration number t is greater than the maximum iteration number T;

[0043] If the iteration number t is greater than the maximum iteration number T, output the current global optimal solution and the current iteration number;

[0044] If the iteration number t is less than the maximum iteration number T, the inertia weight is updated based on a nonlinear change strategy, and the second-order oscillation processing is performed on the particle velocity update, the velocity and position of each particle are updated, the current iteration number t is t+1, and the calculation of the fitness value of each particle is returned to continue.

[0045] The second aspect of the present application provides an artificial intelligence-based power balance generator access scheme design optimization system.

[0046] An artificial intelligence-based power balance generator access scheme design optimization system comprises:

[0047] A data acquisition module is configured to acquire an access scheme obtained according to the type of the power balance generator and the access point of the power balance generator.

[0048] An extreme operating mode set search module is configured to search for an extreme operating mode set under each access scheme based on a bisection method.

[0049] A parameter optimization module is configured to, if the extreme operating mode set under each access scheme is empty, select an access scheme with the lowest cost as the target; otherwise, perform parameter optimization on the access scheme with a non-empty extreme operating mode set based on an improved particle swarm optimization algorithm.

[0050] A scheme selection module is configured to, if the extreme operating mode set searched based on the bisection method under the access scheme after parameter optimization is still not empty, discard the access scheme; otherwise, select an access scheme with an empty extreme operating mode set as the target.

[0051] The third aspect of the present application provides a computer-readable storage medium having a program stored thereon, the program being executed by a processor to implement the steps in the artificial intelligence-based power balance generator access scheme design optimization method according to the first aspect of the present application.

[0052] The fourth aspect of the present application provides an electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor implements the steps in the artificial intelligence-based power balance generator access scheme design optimization method according to the first aspect of the present application when executing the program.

[0053] Compared with the prior art, the present application has the following advantages:

[0054] 1. The application improves the speed and efficiency of searching extreme operating modes under different power balance generator access schemes by searching extreme operating modes under different power balance generator access schemes and optimizing the parameters of controllers such as exciter and speed regulator, and realizes the selection of the most economical, reasonable and reliable power balance generator access power system scheme.

[0055] 2. The power balance generator access scheme design optimization method based on artificial intelligence improves the probability of searching for a global optimal solution and improves the convergence speed of the algorithm, so that the optimized power balance generator access scheme is obtained. BRIEF DESCRIPTION OF DRAWINGS

[0056] The drawings accompanying the specification of this application form a part thereof and serve to further understand the application, the illustrative embodiments thereof and their description are used to explain the application, and do not constitute an improper limitation on the application.

[0057] Figure 1 The grid connection diagram provided for embodiment 1 of the application.

[0058] Figure 2 The improved bisection search method flowchart provided for embodiment 1 of the application.

[0059] Figure 3 The improved particle swarm optimization algorithm flowchart provided for embodiment 1 of the application.

[0060] Figure 4 The 11-node 1000MW generator excitation voltage change curve graph provided for embodiment 1 of the application.

[0061] Figure 5 The 11-node 1000MW generator reactive power change curve graph provided for embodiment 1 of the application.

[0062] Figure 6 The 11-node 1000MW generator active power change curve graph provided for embodiment 1 of the application.

[0063] Figure 7 The 11-node voltage change curve graph provided for embodiment 1 of the application. DETAILED DESCRIPTION

[0064] The application will be further described below in conjunction with the drawings and embodiments.

[0065] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as generally understood by those skilled in the art to which the application belongs.

[0066] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0067] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0068] Example 1:

[0069] like Figures 1-7 As shown, Embodiment 1 of the present invention provides a preferred design method for a power balancing generator access scheme based on artificial intelligence, including the following:

[0070] Based on the type and connection point of the power balancing generator, all possible connection schemes are constructed, specifically including the following eight connection schemes: power balancing synchronous generator connection to the plant power system, power balancing asynchronous generator connection to the plant power system, power balancing synchronous generator connection to the generator outlet, power balancing asynchronous generator connection to the generator outlet, power balancing synchronous motor connection to the plant power system, power balancing asynchronous motor connection to the plant power system, power balancing synchronous motor connection to the generator outlet, and power balancing asynchronous motor connection to the generator outlet.

[0071] Choose one of the above eight options in sequence to connect the power-balancing generator to the power system. The specific selection method includes:

[0072] A voltage safety and stability criterion for the power system is established because the induced draft fan, as the largest capacity motor in the plant's auxiliary load, generates an extremely large starting current during startup. Excessive starting current (4-7 times the rated current under no-load, and 8-10 times or more under load) can cause a drop in grid voltage, endangering system voltage safety, affecting the normal operation of other electrical equipment, and potentially triggering undervoltage protection, leading to harmful equipment tripping. Therefore, the following safety and stability criterion is adopted for grid voltage: the voltage at the node where the motor is located should not fall below 0.8 per-unit values ​​during transient processes.

[0073] The power system frequency safety stability criterion is set. Since the induced draft fan is the largest capacity motor in the plant load, the starting moment will cause power imbalance of the power grid, the generator output torque increases, the speed decreases, and the system frequency decreases, which endangers the system frequency safety. Therefore, the following safety and stability criterion is used for the power grid frequency: the transient frequency of all nodes in the power plant is not less than 49.9 Hz and not higher than 50.1 Hz;

[0074] The power system low-frequency oscillation stability criterion is set. Since the induced draft fan is started, the generators are parallel operation to keep synchronization. When the induced draft fan is started, the power imbalance of the power grid causes the system frequency to decrease. Under this disturbance, the relative swing occurs between the generator rotors, and the oscillation continues when the damping is lacking. If measures are not taken in time, the oscillation will worsen, eventually leading to system instability, splitting, and forming a large-scale power outage accident. Therefore, the following safety and stability criterion is used for the power grid low-frequency oscillation: the damping ratio is less than 0.04 for weak damping, 0.04-0.05 for suitable damping, and higher than 0.05 for high damping ratio system;

[0075] The improved dichotomy search method is used to search the extreme operating mode set under the current access scheme, which specifically includes the following steps:

[0076] It is assumed that the value range of the active power P1 of the 1# side large generator set is [P 1min ,P 1max ], the value range of the active power P2 of the 2# side large generator set is [P 2min ,P 2max ], and they are equally divided into n segments, the active power P1 of the 1# side large generator set is taken as P 1min +jΔP1, and the cycle number j is set as 0;

[0077] For each small segment [P 2,k ,P 2,k+1 ], P 2low =P 2,k and P 2high =P 2,k+1 are taken respectively, the transient voltage value of the node where the motor is located, the transient frequency value of all nodes in the power plant, and the damping ratio are simulated and tested when the active power of the 1# side large generator and the active power of the 2# side large generator are equal to (P1, P 2low ) and (P1, P 2high ) respectively, and the cycle number k is set as 1;

[0078] According to the set power system voltage safety and stability criterion, the power system frequency safety and stability criterion, and the power system low-frequency oscillation stability criterion, the transient stability of the power system under the two operating modes (P1, P 2low ) and (P1, P 2high ) is judged;

[0079] If the system is transiently stable or transiently unstable in both (P1, P 2low ) and (P1, P 2high ), there is no stable boundary point in the segment [P 2,k , P 2,k+1 ], and k=k+1;

[0080] If k>n, j=j+1;

[0081] If j>(P 1max -P 1min ) / ΔP1, the loop is ended and the results are outputted, and if j<(P 1max -P 1min ) / ΔP1, the next j loop is executed;

[0082] If k<n, the next k loop is executed;

[0083] If the system is transiently unstable in (P1, P 2low ) and transiently stable in (P1, P 2high ), P 2medium =(P 2low +P 2high ) / 2 is taken, and the loop number i=1 is set;

[0084] If P 2medium -P 2low <0.01, the stable boundary point of the system in the segment [P 2,k , P 2,k+1 ] is equal to P 2medium , and k=k+1;

[0085] If k>n, j=j+1;

[0086] If j>(P 1max -P 1min ) / ΔP1, the loop is ended and the results are outputted, and if j<(P 1max -P 1min ) / ΔP1, the next j loop is executed;

[0087] If k<n, the next k loop is executed;

[0088] If P 2medium -P 2high >0.01, the transient voltage value of the node where the motor is located, the transient frequency value and the damping ratio of all nodes in the power plant are simulated and tested when the output of the large generator on the 1# side and the output of the large generator on the 2# side are equal to (P1, P 2medium );

[0089] According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system in the (P1, P 2medium ) operating mode is judged.

[0090] If the system is transiently unstable in the (P1, P 2medium ) operating mode, P 2low =P 2medium , if the system is transiently stable in the (P1, P 2medium ) operating mode, P 2high =P 2medium , and i=i+1.

[0091] The stable boundary points obtained by the above process are fitted, and the stable boundary under each access scheme is obtained.

[0092] Finally, the extreme operating mode set under eight access schemes is obtained. If the extreme operating mode set searched based on the improved bisection search method under eight access schemes is empty, it is indicated that the eight schemes are reasonable and reliable in the technical aspect. Next, the eight access schemes are further optimized in the economic aspect, and finally an economic, reasonable and reliable access scheme is selected.

[0093] If the extreme operating mode set searched based on the improved bisection search method under some access schemes is not empty, it is indicated that the several access schemes are not reasonable and reliable in the technical aspect, and the parameters of the exciter, governor and other controllers in the several access schemes need to be optimized based on the improved particle swarm optimization algorithm.

[0094] The specific improved particle swarm optimization algorithm includes the following steps:

[0095] Initialize the particle swarm and set related parameters, including the following parameters:

[0096] Population size: the larger the initial population, the better the convergence, but too large initial population size will affect the speed of the particle swarm algorithm, so the initial population is generally taken as 50-1000;

[0097] Iteration number: too few iterations will lead to unstable solution, and too many iterations will cause time-consuming, so the iteration number is generally taken as 100-4000, and for complex problems, the evolution number can be increased accordingly;

[0098] Inertia weight: this parameter reflects the influence of individual historical performance on the present, and is generally taken as 0.5-1;

[0099] Learning factor: generally taken as 0-4, which is determined according to the value range of the independent variable, and the learning factor is divided into individual and group;

[0100] Space dimension: the space dimension of particle search is the number of independent variables, i.e. the parameters of the exciter, governor and other controllers;

[0101] Position limit: limit the search space of particles, i.e. the value range of independent variables, i.e. the value range of the parameters of the exciter, governor and other controllers;

[0102] Speed limit: if the flying speed of particles is too fast, it is likely to fly directly through the optimal solution position, and if the flying speed of particles is too slow, it will slow down the convergence speed, so it is necessary to set a reasonable speed limit.

[0103] Let the current iteration number t = 1;

[0104] Set the objective function according to the extreme operating mode set searched under the current access scheme;

[0105] Calculate the fitness value of each particle;

[0106] Find the current individual optimal solution p ibest of each particle;

[0107] Find the current global optimal solution p gbest of the entire particle swarm;

[0108] Determine whether the convergence criterion is met, i.e. whether the iteration number t is greater than the maximum iteration number T;

[0109] If the iteration number t is greater than the maximum iteration number T, output the current global optimal solution and the current iteration number;

[0110] If the iteration number t is less than the maximum iteration number T, update the inertia weight based on the nonlinear change strategy and perform second-order oscillation processing on the particle speed update, update the speed and position of each particle, and the current iteration number t = t + 1;

[0111]

[0112]

[0113]

[0114] In the formula, ω(t) is the inertia weight, c1 and c2 are learning factors, generally c1 = c2 = 2, random(0,1) is a random number in the interval [0,1], p id is the d-th dimension of the individual optimal solution of the i-th particle, p gd is the d-th dimension of the global optimal solution, ω max is the initial inertia weight, generally 0.9, and ω minThe inertia weight when the maximum iteration number of the algorithm is 0.4, K is a weight control factor, t is the current iteration number, T is the maximum iteration number, and xi and xi are random numbers.

[0115] When t<=T / 2,

[0116]

[0117] When t>T / 2,

[0118]

[0119] Return to continue to calculate the fitness value of each particle.

[0120] If the extreme operation mode set searched based on the improved dichotomy search method under the optimized several access schemes is empty, the several access schemes are further optimized in the economic aspect, and finally an access scheme that is most economical, reasonable and reliable is selected.

[0121] If the extreme operation mode set searched based on the improved dichotomy search method under the optimized several access schemes is not empty, the several access schemes are discarded, the remaining access schemes are optimized in the economic aspect, and finally an access scheme that is most economical, reasonable and reliable is selected.

[0122] Embodiment 2:

[0123] The embodiment 2 of the present application provides a power balance generator access scheme design optimization system based on artificial intelligence, comprising:

[0124] The data acquisition module is configured to acquire an access scheme obtained according to the type of the power balance generator and the access point of the power balance generator.

[0125] The extreme operation mode set search module is configured to search an extreme operation mode set under each access scheme based on a dichotomy search method.

[0126] The parameter optimization module is configured to, if the extreme operation mode sets under each access scheme are all empty sets, select an access scheme with the lowest cost as the target; otherwise, perform parameter optimization on the access scheme with a non-empty extreme operation mode set based on an improved particle swarm optimization algorithm.

[0127] The scheme selection module is configured to, if the extreme operation mode set searched based on the dichotomy search method under the access scheme after parameter optimization is still not empty, discard the access scheme; otherwise, select an access scheme with an empty extreme operation mode set as the target.

[0128] The working method of the system is the same as the preferred method of the artificial intelligence-based power balance generator access scheme design provided in Embodiment 1, and will not be described here.

[0129] Embodiment 3

[0130] Embodiment 3 of the present application provides a computer readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the preferred method of artificial intelligence-based power balance generator access scheme design as described in Embodiment 1 of the present application.

[0131] Embodiment 4

[0132] Embodiment 4 of the present application provides an electronic device including a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor implements the steps in the preferred method of artificial intelligence-based power balance generator access scheme design as described in Embodiment 1 of the present application when executing the program.

[0133] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer-usable program code.

[0134] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The means for performing the functions specified in one or more flows and / or blocks.

[0135] These computer program instructions can also be stored in a computer-readable memory that can cause the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The means for performing the functions specified in one or more flows and / or blocks.

[0136] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable devices provide a process for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks. Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks.

[0137] Those of ordinary skill in the art can understand that all or part of the flow of the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the flow of the above-mentioned embodiment of each method. Among them, the storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0138] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based power balance generator access scheme design optimization method, characterized in that: it comprises the following processes: obtaining an access scheme according to the type of power balance generator and the access point of the power balance generator; searching for a set of extreme operating modes under each access scheme based on the dichotomy search method, including: Suppose the active power P1 of the generator set on side 1 has a value range of [P 1min , P 1max ] and the active power P2 of the large generator on side 2 has a value range of [P 2min , P 2max ], take the active power P1 of the large generator set on side 1 as P1=P 1min + j P1, and set the cycle number j =0. For each small segment [P 2,k ,P 2,k+1 ], take P 2low =P 2,k , P 2high =P 2,k+1 , respectively, test the transient voltage value of the node where the motor is located, the transient frequency value of all nodes in the power plant and the damping ratio when the output of the large generator on side 1 and the output of the large generator on side 2 are equal to (P1, P 2low ), (P1, P 2high ), respectively, and set the cycle number k =1. According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system under the operation mode of (P1, P 2low ) and (P1, P 2high ) is judged. If the system is transiently stable or transiently unstable in both (P1, P 2low ) and (P1, P 2high ), there is no stable boundary point in the segment [P 2,k , P 2,k+1 ], and k = k +1; If k < / k n < / n then j < / j j < / j +1; If j>(P) 1max -P 1min ) / If P1, then the loop ends and the result is output; if j < (P... 1max -P 1min ) / P1 then proceeds to the next round. j cycle; If k n then perform the next round k of the loop;​ If the system is transiently unstable in (P1, P 2low ) operating mode, it is transiently stable in (P1, P 2high ) operating mode, then P 2medium = (P 2low + P 2high ) / 2, and the cycle number i =1. If P 2medium - 2low <0.01, then the stable boundary point of the system in the interval [P 2,k , P 2,k+1 ] is equal to P 2medium , and k = k +1; If k < / k n < / n If j < / j j < / j +1; If j>(P) 1max -P 1min ) / If P1, then the loop ends and the result is output; if j < (P... 1max -P 1min ) / P1 then proceeds to the next round. j cycle; If k n then the next round k loop is executed.​ If P 2medium - P 2high > 0.01, then test the transient voltage value of the node where the motor is located, the transient frequency value of all nodes in the power plant and the damping ratio when the No. 1 side large generator output and the No. 2 side large generator output are equal to (P1, P 2medium ). According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system in the (P1, P 2medium ) operation mode is judged. If the system is transiently unstable in the (P1, P 2medium ) operating mode, then P 2low = P 2medium , and if the system is transiently stable in the (P1, P 2medium ) operating mode, then P 2high = P 2medium , and i = i +1; fitting the stable boundary points obtained in the above process to obtain the stable boundary under each access scheme, and then obtaining the set of extreme operating modes under each access scheme; if the set of extreme operating modes under each access scheme is empty, selecting the access scheme with the lowest cost as the target; otherwise, performing parameter optimization on the access scheme with a non-empty set of extreme operating modes based on an improved particle swarm optimization algorithm; if the set of extreme operating modes searched based on the dichotomy search method under the access scheme after parameter optimization is still not empty, discarding this access scheme; otherwise, selecting the access scheme with the lowest cost as the target for which the set of extreme operating modes is empty.

2. The artificial intelligence-based power balance generator access scheme design optimization method according to claim 1, characterized in that: the access scheme includes: a power balance synchronous generator access to the plant power system wiring scheme, a power balance asynchronous generator access to the plant power system wiring scheme, a power balance synchronous generator access to the generator outlet wiring scheme, a power balance asynchronous generator access to the generator outlet wiring scheme, a power balance synchronous motor access to the plant power system wiring scheme, a power balance asynchronous motor access to the plant power system wiring scheme, a power balance synchronous motor access to the generator outlet wiring scheme, and a power balance asynchronous motor access to the generator outlet wiring scheme.

3. The artificial intelligence-based power balance generator access scheme design optimization method according to claim 1, characterized in that: the voltage safety and stability criterion of the power system includes that the voltage at the node where the motor is located is not lower than 0.8 per unit value in the transient process.

4. The artificial intelligence-based power balance generator access scheme design optimization method according to claim 1, characterized in that: the frequency safety and stability criterion of the power system includes that the transient frequency of all nodes in the power plant is not lower than 49.9 Hz and not higher than 50.1 Hz.

5. The artificial intelligence-based power balance generator access scheme design optimization method according to claim 1, characterized in that: the low-frequency oscillation stability criterion of the power system includes that a damping ratio lower than 0.04 is weak damping, 0.04-0.05 is suitable damping, and higher than 0.05 is a high damping ratio system.

6. The artificial intelligence-based power balance generator access scheme design optimization method according to claim 1, characterized in that: the particle swarm optimization algorithm includes: initializing the particle swarm and setting the related parameters; Let the current iteration number t = 1; setting the objective function according to the minimum set of extreme operating modes searched under the current access scheme; calculating the fitness value of each particle; finding the current individual optimal solution of each particle; finding the current global optimal solution of the entire particle swarm. determining whether a convergence criterion is satisfied, i.e. whether the iteration number t is greater than a maximum iteration number T; If the number of iterations t If the number of iterations is greater than the maximum number of iterations T, then output the current global optimal solution and the current number of iterations. If the iteration number t is less than the maximum iteration number T, the inertia weight is updated based on the nonlinear change strategy and the second-order oscillation processing is performed on the particle velocity update, the velocity and position of each particle are updated, and the current iteration number t = t +1, and the calculation of the fitness value of each particle is returned to continue.

7. An artificial intelligence-based power balance generator access scheme design optimization system, characterized in that: it comprises: The data acquisition module is configured to acquire an access scheme obtained according to a type of the power balance generator and an access point of the power balance generator; The extreme operating mode set searching module is configured to search for an extreme operating mode set under each access scheme based on a dichotomy method, including: Suppose the active power P1 of the generator set on side 1 has a value range of [P 1min ,P 1max ], the active power P2 of the large generator on side 2 has a value range of [P 2min ,P 2max ], and the active power P1 of the large generator set on side 1 is P1=P 1min + j P1, and the cycle number is j =0; For each small segment [P 2,k ,P 2,k+1 ], take P 2low =P 2,k , P 2high =P 2,k+1 , respectively, test the transient voltage value of the node where the motor is located, the transient frequency value of all nodes in the power plant and the damping ratio when the output of the large generator on side 1 and the output of the large generator on side 2 are equal to (P1, P 2low ), (P1, P 2high ), respectively, and set the cycle number k =1. According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system under the operation mode of (P1, P 2low ) and (P1, P 2high ) is judged. If the system is transiently stable or transiently unstable in both (P1, P 2low ) and (P1, P 2high ), there is no stable boundary point in the segment [P 2,k , P 2,k+1 ], and k = k +1. If k < / k n < / n If j < / j j < / j + 1; If j>(P) 1max -P 1min ) / If P1, then the loop ends and the result is output; if j < (P... 1max -P 1min ) / P1 then proceeds to the next round. j cycle; If k n then perform the next round k of the loop;​ If the system is transiently unstable in (P1, P 2low ) operating mode, and is transiently stable in (P1, P 2high ) operating mode, then P 2medium =(P 2low +P 2high ) / 2, and the cycle number i =1. If P 2medium - 2low <0.01, then the stable boundary point of the system in the interval [P 2,k , 2,k+1 ] is equal to P 2medium , and k = k +1; If k < / k n < / n then j < / j = 0 j < / j + 1; If j>(P) 1max -P 1min ) / If P1, then the loop ends and the result is output; if j < (P... 1max -P 1min ) / P1 then proceeds to the next round. j cycle; If k n then the next round k of the loop is executed.​ If P 2medium - P 2high > 0.01, then test the transient voltage value of the node where the motor is located, the transient frequency value of all nodes in the power plant and the damping ratio when the No. 1 side large generator output and the No. 2 side large generator output are equal to (P1, P 2medium ). According to the set power system voltage safety and stability criterion, power system frequency safety and stability criterion and power system low frequency oscillation stability criterion, the transient stability of the power system in the (P1, P 2medium ) operation mode is judged. If the system is transiently unstable in the (P1, P 2medium ) operating mode, then P 2low = P 2medium , and if the system is transiently stable in the (P1, P 2medium ) operating mode, then P 2high = P 2medium , and i = i +1. The stable boundary points obtained through the above process are fitted to obtain a stable boundary under each access scheme, and then extreme operating mode sets under the respective access schemes are obtained respectively; The parameter optimization module is configured to, if the extreme operating mode sets under the respective access schemes are all empty sets, select the access schemes with the lowest cost as a target; otherwise, perform parameter optimization on the access schemes with the extreme operating mode sets being non-empty sets based on an improved particle swarm optimization algorithm; The scheme selection module is configured to, if the extreme operating mode set searched based on the dichotomy method under the access scheme after the parameter optimization is still a non-empty set, discard the access scheme; otherwise, select the access schemes with the extreme operating mode sets being empty sets as a target.

8. A computer-readable storage medium having stored thereon a program, characterized in that, The program is executed by the processor to implement the steps in the artificial intelligence-based power balance generator access scheme design optimization method according to any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized by The processor executes the program to implement the steps in the artificial intelligence-based power balance generator access scheme design optimization method according to any one of claims 1-6.

Images