CN111796512B - Method, device, equipment and storage medium for determining equipment scheduling parameters - Google Patents
Method, device, equipment and storage medium for determining equipment scheduling parameters Download PDFInfo
- Publication number
- CN111796512B CN111796512B CN201910276337.8A CN201910276337A CN111796512B CN 111796512 B CN111796512 B CN 111796512B CN 201910276337 A CN201910276337 A CN 201910276337A CN 111796512 B CN111796512 B CN 111796512B
- Authority
- CN
- China
- Prior art keywords
- individual
- determining
- learning
- teaching
- individuals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the application discloses a method, a device, equipment and a storage medium for determining equipment scheduling parameters, wherein the method comprises the following steps: selecting scheduling parameters of equipment, and forming corresponding discrete coding vectors based on the scheduling parameters corresponding to different time periods; determining discrete coding vectors with fitness values meeting requirements as teaching individuals; determining an initial discrete coding vector corresponding to the learning individual, determining a cross point according to the total number of time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual; and when the preset termination condition is determined to be met based on the updated learning individual and the updated teaching individual, determining the target scheduling parameter of the equipment according to the discrete coding vectors corresponding to the updated learning individual and the updated teaching individual. The problem of discrete decision optimization can be solved, and the response speed of scheduling parameter optimization control is improved.
Description
Technical Field
The present application relates to the field of device control, and in particular, to a method, an apparatus, a device, and a storage medium for determining a device scheduling parameter.
Background
With the development of artificial intelligence, various devices adopt an intelligent scheduling strategy. For example, for a pumping station for water transfer across a basin, optimal scheduling of the pumping station is an extremely important ring in water transfer engineering. The completion of the water diversion task with the least cost is the key to ensuring that the water diversion project can be continuously developed under the given water diversion target.
In the related art, the scheduling control of a pump station often needs to make a unit in the pump station operate under the optimal working condition according to a target, and a related optimal scheduling algorithm has the defect that the convergence rate needs to be improved in the scheduling parameter optimal control, and is difficult to meet the requirements of the scheduling control.
Disclosure of Invention
In view of this, embodiments of the present application provide a method, an apparatus, a device, and a storage medium for determining a device scheduling parameter, which aim to improve a response speed of scheduling parameter optimization control and meet a requirement of scheduling control.
The technical scheme of the embodiment of the application is realized as follows:
in a first aspect, an embodiment of the present application provides a method for determining a device scheduling parameter, including:
selecting a scheduling parameter of equipment, and forming a corresponding discrete coding vector based on the scheduling parameter corresponding to different time periods;
determining a discrete coding vector with a fitness value meeting requirements as a teaching individual;
determining an initial discrete coding vector corresponding to a learning individual, determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual;
and when the updated learning individual and the updated teaching individual are determined to meet the preset termination condition, determining the target scheduling parameters of the equipment according to the updated discrete coding vectors corresponding to the learning individual and the teaching individual.
In a second aspect, an embodiment of the present application provides a method for determining a scheduling parameter of a pump station based on the method for determining a device scheduling parameter described in the foregoing embodiment, where the pump station includes at least two units, and the scheduling parameter includes at least one of the following: the number of the units, the installation angle of the blades of the units and the running speed of the units.
In a third aspect, an embodiment of the present application provides an apparatus for determining a device scheduling parameter, including:
the encoding module is used for selecting scheduling parameters of equipment and forming corresponding discrete encoding vectors based on the scheduling parameters corresponding to different time periods;
the first determining module is used for determining the discrete coding vector with the adaptability value meeting the requirement as a teaching individual;
the teaching module is used for determining an initial discrete coding vector corresponding to a learning individual, determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual;
and the second determining module is used for determining the target scheduling parameters of the equipment according to the updated discrete coding vectors corresponding to the learning individuals and the teaching individuals when the updated learning individuals and the updated teaching individuals are determined to meet the preset termination conditions.
In a fourth aspect, an embodiment of the present application provides a scheduling parameter determining device, including:
a memory for storing an executable program;
and the processor is used for implementing the device scheduling parameter determining method in the foregoing embodiment when executing the executable program stored in the memory.
In a fifth aspect, an embodiment of the present application provides a computer storage medium, which stores an executable program, and when the executable program is executed by a processor, the method for determining a device scheduling parameter according to the foregoing embodiment is implemented.
According to the technical scheme, corresponding discrete coding vectors are formed based on the scheduling parameters corresponding to different time periods, the discrete coding vectors with the fitness values meeting the requirements are determined as teaching individuals, the intersection points are determined according to the total number of the time periods, the teaching individuals and the learning individuals perform coding exchange based on the intersection points to obtain target coding groups, the learning individuals are updated according to the discrete coding vectors with the fitness values meeting the preset conditions determined by the target coding groups, when the learning individuals and the teaching individuals after updating are determined to meet the preset termination conditions, the target scheduling parameters of the equipment are determined according to the discrete coding vectors corresponding to the learning individuals and the teaching individuals after updating, so that the scheduling scheme of the equipment is generated, the problem of performing optimization decision on the discrete scheduling parameters is solved, the information of the teaching individuals is transmitted to the learning individuals as much as possible through the crossover algorithm, the problem of optimizing decision can be solved compared with the traditional teaching and learning optimization algorithm, the operation efficiency of the crossover algorithm is high, the response speed of optimization control of the scheduling parameters is improved, and the requirement of scheduling control is met.
Drawings
Fig. 1 is a schematic flowchart of a method for determining a device scheduling parameter according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a method for determining scheduling parameters of a pump station according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an apparatus for determining device scheduling parameters according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for determining device scheduling parameters according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a scheduling parameter determining device according to an embodiment of the present application.
Detailed Description
The technical solution of the present application is further described in detail with reference to the drawings and specific embodiments. It should be understood that the examples provided herein are merely illustrative of the present application and are not intended to limit the present application. In addition, the following examples are provided for the purpose of carrying out some embodiments of the present application, and not for the purpose of providing all embodiments for carrying out the present application, and the technical solutions described in the embodiments of the present application may be implemented in any combination without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
An embodiment of the present application provides a method for determining a device scheduling parameter, please refer to fig. 1, where the method includes:
Here, the selected scheduling parameters are encoded based on different time periods to form discrete encoded vectors. The scheduling parameter here may be one or more. When the scheduling parameter is multiple, a discrete coding vector corresponding to each scheduling parameter is formed. The scheduling parameter may be an electrical parameter used to determine the operational performance of the device, such as operating current, voltage, or other performance parameters.
In this embodiment, for each scheduling parameter, a corresponding discrete coding vector group is randomly generated, where the discrete coding vector group includes a plurality of discrete coding vectors as individuals, which is convenient for subsequent teaching operations.
In one embodiment, the equipment takes a pump station as an example, the pump station has JZ sets, the blade setting angle of the set is designed to be 0 degrees, and the value range of the blade setting angle is [ -a °, + a ° ]]Discrete at 1 degree interval to obtain 2a +1 degree value [ -a ° ], - (a-1) ° 0 ° ], { a-1) ° a ° c]. A day is divided into SN periods. The scheduling parameters of the device may include: the number of units and the blade placement angle. For example, the discrete code vector corresponding to the unit operation number is BN = (b) 1 ,b 2 ,...,b i ,...b SN ) Wherein, b i Representing the unit operation number in the time period i; the discrete code vector corresponding to the blade setting angle is AN = (a) 1 ,a 2 ,...,a i ,...,a SN ) Wherein a is i Representing the blade setting angle at time period i. The BN and AN together constitute a single individual code. Randomly generating C pairs of BN and AN codes (BN and AN form AN individual X) according to the value range of the unit operation number and the value range of the blade mounting angle i ) Therefore, the initialization of the class is completed, and the subsequent teaching operation is facilitated.
And 102, determining the discrete coding vector with the adaptability value meeting the requirement as a teaching individual.
And determining the fitness value of the discrete coding vector corresponding to the scheduling parameter according to a preset objective function. The objective function is determined based on the scheduling parameters as input, target parameters as output and constraints of the equipment operation, wherein the target parameters are statistical parameters based on a plurality of time periods. It should be noted that different objective functions may be set for different objective parameters.
In an embodiment, the optimal scheduling problem of the pump station is a complex optimal problem, and under the condition of considering single scheduling operation, the power consumption cost of a unit in scheduling is the largest one of the whole scheduling cost. Considering that a large pump station is not suitable for frequent startup and shutdown, time-of-use electricity price and other factors, dividing one day into SN time intervals, regarding a pump station with a JZ set, taking total electricity consumption cost as a target parameter, taking the number of started pumps and blade placement angles in each time interval as scheduling parameters, and taking water lifting amount and power as constraint conditions, obtaining a corresponding target function of the pump station as follows:
an objective function:
and (3) water lifting amount constraint:
and (3) power constraint: n is a radical of i (θ i )≤N 0
Wherein the specific meanings of the variables are as follows:
in this embodiment, the discrete coding vector with the optimal fitness value (i.e., the lowest power consumption cost) in the "class" is determined as the teaching individual according to the objective function f.
In this embodiment, the learning individuals refer to other individuals except the teaching individuals in the randomly generated "class", and each learning individual has an initial discrete encoding vector that is randomly generated. In order to transfer the 'knowledge' of the teaching individual to the learning individual as much as possible, the 'achievement' of the learning individual is gradually improved. The embodiment adopts the single-point crossing algorithm to perform teaching operation, has large exchange area, can acquire more excellent coding information of teaching individuals, and has simple operation and high efficiency.
For example, the discrete code vector of teaching individual T is
For any learning individual X j Which is coded as
The teaching operation based on the single-point crossing algorithm comprises the following specific steps:
step1: randomly generating a cross point P which belongs to [1, SN-1];
step2: mixing T and X j The code exchange after the individual code cross point P can obtain the following four groups of discrete code vectors:
step3: calculating X ', X' according to the target function f X "" one of four sets of discrete encoding vectors having the smallest fitness value, Y = argmin (f (X '), f (X "), f (X')), then Y is X after the teaching operation of this time j Updating corresponding discrete coding vector and corresponding to X j And (6) updating.
And 104, when the preset termination condition is met based on the updated learning individuals and teaching individuals, determining target scheduling parameters of the equipment according to the updated discrete coding vectors corresponding to the learning individuals and the teaching individuals.
Judging whether the preset termination condition is met or not, and determining the target scheduling parameter of the equipment according to the discrete coding vector with the optimal fitness value in the updated learning individual and teaching individual (namely the updated 'class') when the preset termination condition is met based on the updated learning individual and teaching individual. Optionally, a corresponding target parameter value may also be determined based on the target function f according to the target scheduling parameter.
Optionally, in an embodiment, when it is determined that the learning individual and the teaching individual do not meet the preset termination condition based on the updated learning individual and teaching individual, the step of returning the discrete coding vector with the determined fitness value meeting the requirement as the teaching individual (i.e. step 102) is performed to re-determine the teaching individual of the "class" and perform the teaching operation with the re-determined teaching individual.
Determining whether a preset termination condition is met or not based on the updated learning individual and the updated teaching individual, wherein the preset termination condition comprises at least one of the following conditions: whether the updating times of the learning individuals meet a first set threshold value or not; whether the optimal fitness value corresponding to the learning individual meets a second set threshold value or not is judged; and whether the difference value between the optimal fitness value corresponding to the current learning individual and the historical optimal fitness value accords with a third set threshold value or not.
In an embodiment, when the number of times of teaching operations on a teaching individual reaches a first set threshold, a discrete coding vector with an optimal fitness value is selected according to the updated class, and then a target scheduling parameter of the device is determined.
In an embodiment, when the optimal fitness value corresponding to the learning individual meets the second set threshold, the optimal fitness value is determined to meet the set requirement of the target parameter, the discrete coding vector with the optimal fitness value is selected according to the updated class, and then the target scheduling parameter of the equipment is determined.
In an embodiment, when a difference between the optimal fitness value corresponding to the current learning individual and the historical optimal fitness value meets a third set threshold, that is, the difference value of knowledge evolution meets the set requirement is indicated, the discrete coding vector with the optimal fitness value is selected according to the updated class, and then the target scheduling parameter of the device is determined.
According to the method and the device, the problem of Optimization decision of discrete scheduling parameters is solved, information of Teaching individuals is transmitted to Learning individuals as much as possible through a cross algorithm, compared with a traditional Teaching and Learning Optimization algorithm (TLBO), the method and the device can solve the problem of Optimization decision of discrete decision, the operation efficiency of the cross algorithm is high, and the response speed of Optimization control of the scheduling parameters is improved.
Optionally, in some embodiments, before determining that the preset termination condition is met based on the updated learning individual and teaching individual, the method for determining the device scheduling parameter may further include: and carrying out the intra-group competitive learning operation on the learning individuals.
And performing an intra-group competitive learning operation on the learning individuals, wherein the operation comprises the following steps:
grouping a plurality of the learning individuals to obtain at least two groups;
selecting any initial individual for each group and determining target individuals, of which the fitness values meet preset conditions, in the group except the selected initial individuals;
and determining a discrete coding vector with the optimal fitness value after the initial individual and the target individual are crossed based on a single-point crossing algorithm, and updating the initial individual according to the discrete coding vector with the optimal fitness value.
The traditional learning operator of TLBO selects one student from classes at random for competitive learning, the mode has high randomness and is not beneficial to the convergence of classes, and the formula provided by the learning operator is designed aiming at continuous variables and cannot be applied to decision optimization of discrete parameters. The embodiment of the application adopts the competing learning operation in the group, and is beneficial to improving the convergence of the learning operation.
In an example, at the time of class initialization, each generated individual is numbered and randomly grouped according to the number, and for a class with the size of C, the individual data of each group is assumed to be G, and the class can be divided into C/G groups (when the scale of the class and the number of individuals in the group are designed, the ratio of the scale to the number of individuals in the group can be considered to be a positive integer).
For any group G i Any member of the group of individuals X j Which is coded as
Then competing learning operations within the group may include:
step1: calculating the intra-group division X according to the fitness function f j Individual X with optimal external fitness best Which is coded as
Step2: calculating X by adopting single-point cross operator j And X best The discrete coding vector Z with the optimal fitness is generated after the intersection, and then the discrete coding vector Z is X after the learning operation j An updated discrete encoded vector.
Optionally, in some embodiments, before determining that the preset termination condition is met based on the updated learning individual and teaching individual, the method for determining the device scheduling parameter may further include: and carrying out self-learning operation on the learning individual based on the basic bit variation.
Performing self-learning operation on the learning individual based on the basic bit variation, comprising:
randomly generating variation positions corresponding to the discrete coding vectors of the learning individuals;
randomly selecting a numerical value from the range value of the scheduling parameter, and replacing the variation position in the discrete coding vector of the learning individual with the numerical value;
the self-learning behavior of the learning individuals in the class can be simulated by carrying out the self-learning operation on the learning individuals based on the basic bit variation, and the individual diversity and the algorithm searching range in the class are improved.
In an example, aiming at the defect that the TLBO algorithm is easy to fall into local optimization, the self-learning behavior of the individual learning in the class is simulated, and the self-learning operation is added. For any learning individual X j A discrete coded vector of
The self-learning operation may include:
step1: randomly generating variant positions P, P being [1, SN ]
Step2: number of runs from the unit [1, JZ ]]Randomly selecting a number jz from the BN to obtain BN j The data at the P position is replaced by jz to obtain the mutated position
Step3: setting an angular discrete set [ -a °, - (a-1) °,0 °,. (a-1) °, a °,]randomly selecting a blade angle degree a, and calculating AN j Replacing the degree of the P position with a to obtain the mutated
The embodiment of the present application further provides a method for determining a scheduling parameter of a pump station, where the pump station includes at least two units, and the scheduling parameter includes at least one of the following: the number of units, the placement angle of the blades of the units and the running speed of the units are controlled by the pump station control method according to any one of the embodiments.
Referring to fig. 2, in an embodiment, a method for determining a scheduling parameter of a pump station may include:
The pump station has a JZ set, the blade setting angle of the set is designed to be 0 degrees, and the value ranges of the blade setting angle are [ -a °, + a ° ]]Discrete at 1 degree interval to obtain 2a +1 degree value [ -a ° ], - (a-1) ° 0 ° ], { a-1) ° a ° c]. A day is divided into SN periods. Of devicesThe scheduling parameters may include: the number of units and the blade placement angle. For example, the discrete code vector corresponding to the unit operation number is BN = (b) 1 ,b 2 ,...,b i ,...b SN ) Wherein b is i Representing the unit operation number in the time period i; the discrete code vector corresponding to the blade placement angle is AN = (a) 1 ,a 2 ,...,a i ,...,a SN ) Wherein a is i Representing the blade setting angle at time period i. The BN and AN together constitute a single individual code. Randomly generating C pairs of BN and AN codes (BN and AN form AN individual X) according to the value range of the unit operation number and the value range of the blade mounting angle i ) Therefore, the initialization of the class is completed, and the subsequent teaching operation is facilitated.
Taking total power consumption as a target parameter, taking the number of started units and the blade placement angle in each time period as scheduling parameters, and taking the water lifting amount and the power as constraint conditions, a target function corresponding to the pump station can be obtained as follows:
an objective function:
and (3) water lifting amount constraint:
and (3) power constraint: n is a radical of i (θ i )≤N0
Wherein the specific meanings of the variables are as follows:
and determining the discrete coding vector with the optimal fitness value (namely, the minimum power consumption cost) in the class as a teaching individual according to the objective function f.
And step 203, performing teaching operation on the learning individuals in the class according to the teaching individuals.
In this embodiment, the learning individuals refer to other individuals except the teaching individuals in the class, and each learning individual has a corresponding discrete coding vector. In order to transfer the 'knowledge' of the teaching individual to the learning individual as much as possible, the 'achievement' of the learning individual is gradually improved. The embodiment adopts the single-point crossing algorithm to perform teaching operation, has large exchange area, can acquire more excellent coding information of teaching individuals, and has simple operation and high efficiency.
For example, the discrete code vector of teaching individual T is
For any learning individual X j Which is coded as
The teaching operation based on the single-point crossing algorithm comprises the following specific steps:
step1: randomly generating a cross point P, wherein the P belongs to [1, SN-1];
step2: combining T and X j After the individual codes cross point P, the code exchange can obtain the following four groups of discrete code vectors:
step3: calculating X ', X' according to the target function f X "" one of the four sets of discrete encoded vectors with the smallest fitness value, Y = argmin (f (X '), f (X "), f (X')), then Y is X after the teaching operation of this time j Updating corresponding discrete coding vector and corresponding to X j And (6) updating.
And step 204, performing the learning operation of competition in the group on the learning individuals.
When the class is initialized, each generated individual is numbered and randomly grouped according to the number, and for a class with the size of C, the individual data of each group is G, and the class can be divided into C/G groups (when the scale of the class and the number of the individuals in the group are designed, the ratio of the scale to the number of the individuals in the group can be considered to be a positive integer).
For any group G i Any member of the group of individuals X j Which is coded as
Then competing learning operations within the group may include:
step1: calculating the intra-group division X according to the fitness function f j Individual X with optimal external fitness best Which is coded as
Step2: calculating X by adopting single-point cross operator j And X best The discrete coding vector Z with the optimal fitness is generated after the intersection, and then the discrete coding vector Z is X after the learning operation j An updated discrete encoded vector.
Optionally, in some embodiments, before determining that the preset termination condition is met based on the updated learning individual and teaching individual, the method for determining the device scheduling parameter may further include: and carrying out self-learning operation on the learning individuals based on the basic bit variation.
Performing self-learning operation on the learning individual based on the basic bit variation, comprising:
randomly generating variation positions corresponding to the discrete coding vectors of the learning individuals;
and randomly selecting a numerical value from the range values of the scheduling parameters, and replacing the variation position in the discrete coding vector of the learning individual with the numerical value.
And step 205, performing self-learning operation on the learning individuals based on the basic bit variation.
The embodiment of the application simulates the self-learning behavior of the individual learning in the class, and adds self-learning operation. For any learning individual X j Whose discrete coded vector is
The self-learning operation may include:
step1: randomly generating variant positions P, P being [1, SN ]
Step2: number of runs from the unit [1, JZ ]]Randomly selecting a number jz from the BN to obtain BN j The data at the P position is replaced by jz to obtain the mutated position
Step3: discrete sets of blade setting angles [ -a °, - (a-1) °, ·,0 °,. (a-1) °, a ° f]Randomly selecting a blade angle degree a, and determining AN j Replacing the degree of the P position with a to obtain the mutated
Here, the determining whether the preset termination condition is met includes at least one of: whether the updating times of the learning individuals meet a first set threshold value or not; whether the optimal fitness value corresponding to the learning individual meets a second set threshold value or not is judged; and whether the difference value between the optimal fitness value corresponding to the current learning individual and the historical optimal fitness value accords with a third set threshold value or not.
If the preset termination condition is determined to be met, step 207 is executed, and if the preset termination condition is determined not to be met, the process returns to step 202.
And determining the target scheduling parameters of the equipment according to the discrete coding vectors with the optimal fitness values in the updated learning individuals and the teaching individuals (namely the updated classes). Optionally, a corresponding target parameter value may also be determined based on the target function f according to the target scheduling parameter.
The method and the device solve the problem of optimization decision of discrete scheduling parameters of the pump station, transmit the information of the teaching individuals to the learning individuals as much as possible through the cross algorithm, can solve the problem of optimization decision of discrete decision compared with the traditional teaching and learning optimization algorithm, are high in operation efficiency of the cross algorithm, and improve the response speed of optimization control of the scheduling parameters of the pump station.
An apparatus for determining a device scheduling parameter is further provided in an embodiment of the present application, please refer to fig. 3, where the apparatus includes:
the encoding module 301 is configured to select a scheduling parameter of a device, and form a corresponding discrete encoding vector based on the scheduling parameter corresponding to different time periods;
a first determining module 302, configured to determine a discrete coding vector whose fitness value meets requirements as a teaching individual;
the teaching module 303 is configured to determine an initial discrete coding vector corresponding to a learning individual, determine an intersection according to the total number of the time periods, perform coding exchange on the teaching individual and the learning individual based on the intersection to obtain a target coding group, and determine a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual;
and a second determining module 304, configured to determine, when it is determined that the updated learning individual and the updated teaching individual meet the preset termination condition, a target scheduling parameter of the device according to the updated discrete coding vectors corresponding to the learning individual and the updated teaching individual.
In some embodiments, the encoding module 301 randomly generates a corresponding discrete encoding vector set for each scheduling parameter, where the discrete encoding vector set includes a plurality of discrete encoding vectors as individuals, so as to facilitate subsequent teaching operations.
In some embodiments, the first determining module 302 is configured to determine the fitness value of the discrete coding vector corresponding to the scheduling parameter according to a preset objective function. And determining the target function based on the scheduling parameters as input, target parameters as output and constraint conditions of the equipment operation, wherein the target parameters are statistical parameters based on a plurality of time periods. It should be noted that different objective functions may be set for different objective parameters.
In some embodiments, tutorial module 303 performs the tutorial operation based on a single point crossover algorithm.
In some embodiments, the first determining module 302 is further configured to, when it is determined that the learning individual and the teaching individual do not meet the preset termination condition based on the updated learning individual and teaching individual, re-determine the discrete encoding vector with the fitness value meeting the requirement as the teaching individual.
In some embodiments, referring to fig. 4, the apparatus scheduling parameter determining device further includes a determining module 307, configured to determine whether a preset termination condition is met based on the updated learning individual and teaching individual, where the preset termination condition includes at least one of: whether the updating times of the learning individuals meet a first set threshold value or not; whether the optimal fitness value corresponding to the learning individual meets a second set threshold value or not is judged; and whether the difference value between the optimal fitness value corresponding to the current learning individual and the historical optimal fitness value accords with a third set threshold value or not.
In some embodiments, an intra-group competition module 305 is further included to: grouping a plurality of the learning individuals to obtain at least two groups; selecting any initial individual for each group and determining target individuals, of which the fitness values meet preset conditions, in the group except the selected initial individuals; and determining a discrete coding vector with the optimal fitness value after the initial individual and the target individual are crossed based on a single-point crossing algorithm, and updating the initial individual according to the discrete coding vector with the optimal fitness value.
In some embodiments, a self-learning module 306 is also included for: randomly generating variation positions corresponding to the discrete coding vectors of the learning individuals; randomly selecting a numerical value from the range value of the scheduling parameter, and replacing the variation position in the discrete coding vector of the learning individual with the numerical value; the self-learning behavior of the learning individuals in the class can be simulated by carrying out the self-learning operation on the learning individuals based on the basic bit variation, and the individual diversity and the algorithm search range in the class are improved.
It should be noted that: in the device scheduling parameter determining apparatus provided in the foregoing embodiment, when determining the scheduling parameter, the foregoing division of each program module is merely used as an example, and in practical applications, the foregoing processing allocation may be completed by different program modules as needed, that is, the internal structure of the apparatus is divided into different program modules, so as to complete all or part of the foregoing processing. In addition, the device scheduling parameter determining apparatus and the device scheduling parameter determining method provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments and are not described herein again.
The embodiment of the application also provides scheduling parameter determining equipment which can be a client, a server, a cloud server and the like. Fig. 5 shows only an exemplary structure of the scheduling parameter determining apparatus, not the entire structure, and a part of or the entire structure shown in fig. 5 may be implemented as necessary.
The scheduling parameter determining apparatus 400 provided in the embodiment of the present application includes: at least one processor 401, memory 402, a user interface 403, and at least one network interface 404. The various components in the scheduling parameter determination device 400 are coupled together by a bus system 405. It will be appreciated that the bus system 405 is used to enable communications among the components of the connection. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 405 in fig. 5.
The user interface 403 may include, among other things, a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touch pad, a touch screen, or the like.
It will be appreciated that the memory 402 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory.
The memory 402 in the embodiment of the present application is used to store various types of data to support the execution of the scheduling parameter determination method. Examples of such data include: any executable program for running on the scheduling parameter determining device 400, such as the executable program 4021, and a program that implements the scheduling parameter determining method of the embodiment of the present application may be contained in the executable program 4021.
The scheduling parameter determination method disclosed in the embodiment of the present application may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the scheduling parameter determination method may be implemented by hardware integrated logic circuits or instructions in the form of software in the processor 401. The Processor 401 described above may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 401 may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium located in the memory 402, and the processor 401 reads the information in the memory 402, and completes the steps of the scheduling parameter determining method provided in the embodiments of the present application in combination with the hardware thereof.
An embodiment of the present application further provides a readable storage medium, where the storage medium may include: various media that can store program codes, such as a removable Memory device, a Random Access Memory (RAM), a Read-Only Memory (ROM), a magnetic disk, or an optical disk. The readable storage medium stores an executable program; the executable program is used for realizing the scheduling parameter determination method in any embodiment of the application when being executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, embodiments of the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing system to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing system, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing system to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing system to cause a series of operational steps to be performed on the computer or other programmable system to produce a computer implemented process such that the instructions which execute on the computer or other programmable system provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for determining device scheduling parameters, comprising:
selecting scheduling parameters of equipment, and forming corresponding discrete coding vectors based on the scheduling parameters corresponding to different time periods;
determining discrete coding vectors with fitness values meeting requirements as teaching individuals;
determining an initial discrete coding vector corresponding to a learning individual, determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual; wherein the learning individuals are other randomly generated individuals except for the teaching individuals; determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual by adopting a single-point cross algorithm;
when the learning individual and the teaching individual are determined to meet the preset termination condition based on the updated learning individual and the updated teaching individual, determining a target scheduling parameter of the equipment according to the discrete coding vectors corresponding to the updated learning individual and the updated teaching individual;
before determining that the preset termination condition is met based on the updated learning individual and the updated teaching individual, the method further comprises the following steps:
performing an intra-group competitive learning operation on the learning individuals, comprising:
grouping a plurality of the learning individuals to obtain at least two groups;
selecting any initial individual for each group and determining target individuals, of which the fitness values meet preset conditions, in the group except the selected initial individuals;
and determining a discrete coding vector with the optimal fitness value after the initial individual and the target individual are crossed based on a single-point crossing algorithm, and updating the initial individual according to the discrete coding vector with the optimal fitness value.
2. The device scheduling parameter determining method of claim 1, further comprising:
and returning the discrete coding vector with the determined fitness value meeting the requirement as the teaching individual when the learning individual and the teaching individual do not meet the preset termination condition based on the updated learning individual and the updated teaching individual.
3. The device scheduling parameter determining method of claim 1, before determining that a preset termination condition is met based on the updated learning individual and teaching individual, further comprising:
performing self-learning operation on the learning individual based on the basic bit variation, comprising:
randomly generating variation positions corresponding to the discrete coding vectors of the learning individuals;
and randomly selecting a numerical value from the range values of the scheduling parameters, and replacing the variation position in the discrete coding vector of the learning individual with the numerical value.
4. The device scheduling parameter determining method of claim 1, further comprising:
and determining the fitness value of the discrete coding vector corresponding to the scheduling parameter according to a preset objective function.
5. The device scheduling parameter determination method of claim 4,
and determining the target function based on the scheduling parameters as input, target parameters as output and constraint conditions of the equipment operation, wherein the target parameters are statistical parameters based on a plurality of time periods.
6. The device scheduling parameter determining method of claim 1 wherein determining whether a preset termination condition is met based on the updated learning individual and teaching individual comprises at least one of:
whether the updating times of the learning individuals meet a first set threshold value or not;
whether the optimal fitness value corresponding to the learning individual meets a second set threshold value or not is judged;
and whether the difference value between the optimal fitness value corresponding to the current learning individual and the historical optimal fitness value accords with a third set threshold value or not.
7. A method for determining scheduling parameters of a pumping station based on the method for determining scheduling parameters of devices according to any one of claims 1 to 6, wherein the pumping station comprises at least two units, and the scheduling parameters include at least one of the following: the number of the units, the mounting angles of the blades of the units and the running speed of the units.
8. An apparatus for determining device scheduling parameters, comprising:
the encoding module is used for selecting scheduling parameters of equipment and forming corresponding discrete encoding vectors based on the scheduling parameters corresponding to different time periods;
the first determining module is used for determining the discrete coding vector with the adaptability value meeting the requirement as a teaching individual;
the teaching module is used for determining an initial discrete coding vector corresponding to a learning individual, determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual; wherein the learning individuals are other randomly generated individuals except the teaching individuals; determining a cross point according to the total number of the time periods, performing coding exchange on the teaching individual and the learning individual based on the cross point to obtain a target coding group, and determining a discrete coding vector with a fitness value meeting a preset condition according to the target coding group to update the learning individual by adopting a single-point cross algorithm;
the second determining module is used for determining a target scheduling parameter of the equipment according to the discrete coding vectors corresponding to the updated learning individual and the updated teaching individual when the learning individual and the updated teaching individual are determined to meet the preset termination condition;
before determining that the preset termination condition is met based on the updated learning individual and the updated teaching individual, the method further comprises the following steps:
performing an intra-group competitive learning operation on the learning individuals, comprising:
grouping a plurality of the learning individuals to obtain at least two groups;
selecting any initial individual for each group and determining target individuals, of which the fitness values meet preset conditions, in the group except the selected initial individuals;
and determining a discrete coding vector with the optimal fitness value after the initial individual and the target individual are crossed based on a single-point crossing algorithm, and updating the initial individual according to the discrete coding vector with the optimal fitness value.
9. A scheduling parameter determining device, comprising:
a memory for storing an executable program;
a processor for implementing the method of determining device scheduling parameters according to any of claims 1 to 6 when executing the executable program stored in the memory.
10. A computer storage medium, characterized in that an executable program is stored, which when executed by a processor, implements the device scheduling parameter determining method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910276337.8A CN111796512B (en) | 2019-04-08 | 2019-04-08 | Method, device, equipment and storage medium for determining equipment scheduling parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910276337.8A CN111796512B (en) | 2019-04-08 | 2019-04-08 | Method, device, equipment and storage medium for determining equipment scheduling parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111796512A CN111796512A (en) | 2020-10-20 |
| CN111796512B true CN111796512B (en) | 2022-10-18 |
Family
ID=72805623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910276337.8A Active CN111796512B (en) | 2019-04-08 | 2019-04-08 | Method, device, equipment and storage medium for determining equipment scheduling parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111796512B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033100B (en) * | 2021-03-29 | 2022-11-29 | 重庆大学 | Cloud manufacturing service combination method based on hybrid teaching optimization algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843197B (en) * | 2016-05-26 | 2017-05-31 | 江南大学 | Discrete Production Workshop static scheduling optimization system based on learning aid algorithm |
| CN107065520B (en) * | 2016-12-09 | 2019-11-05 | 聊城大学 | A kind of air-cooler parameter configuration optimization method |
-
2019
- 2019-04-08 CN CN201910276337.8A patent/CN111796512B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111796512A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | A discrete artificial bee colony algorithm for distributed hybrid flowshop scheduling problem with sequence-dependent setup times | |
| Li et al. | Efficient multi-objective optimization algorithm for hybrid flow shop scheduling problems with setup energy consumptions | |
| Feng et al. | Optimization of hydropower reservoirs operation balancing generation benefit and ecological requirement with parallel multi-objective genetic algorithm | |
| CN107995039B (en) | Resource self-learning and self-adaptive distribution method for cloud software service | |
| Simaria et al. | A genetic algorithm based approach to the mixed-model assembly line balancing problem of type II | |
| Karthikeyan et al. | A hybrid discrete firefly algorithm for solving multi-objective flexible job shop scheduling problems | |
| Ozturk et al. | Extracting priority rules for dynamic multi-objective flexible job shop scheduling problems using gene expression programming | |
| CN106610867B (en) | On-chip network task scheduling method and device | |
| CN101901425A (en) | Flexible job shop scheduling method based on multi-species coevolution | |
| García-Galán et al. | Rules discovery in fuzzy classifier systems with PSO for scheduling in grid computational infrastructures | |
| CN109829582A (en) | Course line speed of a ship or plane optimization method and system | |
| Xu et al. | An effective shuffled frog-leaping algorithm for solving the hybrid flow-shop scheduling problem with identical parallel machines | |
| Lim et al. | A self-adaptive topologically connected-based particle swarm optimization | |
| Xie et al. | An effective multi-objective artificial bee colony algorithm for energy efficient distributed job shop scheduling | |
| CN111796512B (en) | Method, device, equipment and storage medium for determining equipment scheduling parameters | |
| CN110471274A (en) | Based on the machine components process line dispatching method for improving unified particle swarm algorithm | |
| Wang et al. | Adaptive backtracking search optimization algorithm with pattern search for numerical optimization | |
| CN115543556A (en) | Adaptive symbolic regression method based on multitask genetic programming algorithm | |
| Fu et al. | A multi-objective pigeon inspired optimization algorithm for fuzzy production scheduling problem considering mould maintenance | |
| Bhatnagar et al. | Stochastic algorithms for discrete parameter simulation optimization | |
| Ujazdowski et al. | Task scheduling–review of algorithms and analysis of potential use in a biological wastewater treatment plant | |
| Liu et al. | An estimation of distribution algorithm with multiple intensification strategies for two-stage hybrid flow-shop scheduling problem with sequence-dependent setup time | |
| Li et al. | Evolutionary multitasking via reinforcement learning | |
| CN112148446B (en) | Evolutionary strategy method for multi-skill resource limited project scheduling | |
| Wang et al. | Iot-based distributed simulation of industrial automation production line management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |