CN114839940A - Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution - Google Patents
Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution Download PDFInfo
- Publication number
- CN114839940A CN114839940A CN202210463887.2A CN202210463887A CN114839940A CN 114839940 A CN114839940 A CN 114839940A CN 202210463887 A CN202210463887 A CN 202210463887A CN 114839940 A CN114839940 A CN 114839940A
- Authority
- CN
- China
- Prior art keywords
- coding
- adaptive evolution
- balance index
- dynamic scheduling
- cross
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- 101150000810 BVES gene Proteins 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 230000001174 ascending effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000002787 reinforcement Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution, and relates to the technical field of workshop dynamic scheduling. The method comprises the following specific steps: discrete indirect coding is carried out on the task to be scheduled; after the discrete indirect coding is completed, traversing the codes so as to convert the sequences, and generating new coding individuals by adopting an operator based on the exchange sequences; and evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on balance indexes, wherein evaluation results are used as indexes of parent individual selection and local search selection. By designing a discrete indirect variable coding form, the invention avoids the generation of an infeasible solution, thereby improving the solving speed of the algorithm; and the new solution generation operator based on the exchange sequence can generate individuals quickly and efficiently. Meanwhile, the algorithm is applied to the scheduling problem under different scenes in a stable effect by combining a self-adaptive evolution strategy based on balance indexes, and the method has good solving speed.
Description
Technical Field
The invention relates to the technical field of workshop dynamic scheduling, in particular to a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution.
Background
Because different manufacturing fields have certain similarity, the cross-domain synergy effect is good due to the complementary synergy in each field in the distributed workshop environment. And the tasks and the environment can have dynamic changes and the complex characteristics of a cross-domain cooperation scene, so that the traditional method is difficult to realize the cross-domain cooperation distributed workshop dynamic scheduling.
In the prior art, some methods consider the idea of using conventional algorithm improvements in combination with other algorithms for dynamic scheduling. Due to the fact that the algorithm simplifies the scene and does not consider the heterogeneity of related problems, the distributed workshop environment is difficult to be refined and solved, and reasonable and balanced utilization of resources cannot be achieved. In a cross-domain collaborative optimization problem, the problem is generally characterized by more uncertain factors, and the algorithm has poor robustness in the solving process and is difficult to meet the self-adaptive requirement.
Still other methods contemplate predicting task requirements using reinforcement learning and deep learning models and scheduling small independent or flow-type tasks. The existing reinforcement learning algorithm is combined with a deep neural network, model training is carried out by utilizing industrial big data such as the change of user requirements and the mobility of Internet of things equipment, and a part of reinforcement learning model is designed for the problem of distributed workshop dynamic scheduling. However, the existing reinforcement learning model is only suitable for a specific scene; when tasks, resources, environments and scheduling targets change, the model is not applicable and needs to be retrained for a new scene, so that the problem that the dynamic scheduling algorithm based on reinforcement learning is difficult to adapt is solved, prior knowledge is not needed in reinforcement learning, and a large amount of data is needed to support model training, so that the model learning efficiency is low and the time is long.
Therefore, for those skilled in the art, how to solve the disadvantages of poor adaptivity and slow solving speed of the dynamic scheduling algorithm is an urgent problem to be solved.
Disclosure of Invention
In view of the above, the invention provides a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution, so as to solve the problems in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme: a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution comprises the following specific steps:
discrete indirect coding is carried out on the task to be scheduled;
after the discrete indirect coding is completed, traversing the codes so as to convert the sequences, and generating new coding individuals by adopting an operator based on the exchange sequences;
and evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on balance indexes, wherein evaluation results are used as indexes of parent individual selection and local search selection.
Optionally, the specific process of the discrete indirect encoding is as follows: when n calculation tasks and m manufacturing tasks are to be scheduled, the coding bit is divided into two parts, namely the manufacturing tasks and the calculation tasks, the lengths of the two parts are n and m respectively, the values of the two parts are positive integers between 0 to (n-1) and 0 to (m-1), and all the positive integers in the value range are covered.
Optionally, the operation process of the exchange sequence is as follows: selecting Pop1 and Pop2 as parent individuals as an implementation object and a reference object respectively, and setting the exchange probability to be 0.5; traversing the numerical value on each coding bit in the Pop1, searching the position in the Pop2, obtaining an exchange pair with the probability of 0.5, finally obtaining an exchange pair sequence from the Pop2 to the Pop1, and operating the individual according to the exchange pair sequence to obtain a new coding individual.
Optionally, the adaptive evolution strategy based on the balance index is as follows:
respectively calculating the diversity component and the convergence component of each individual in the population;
weighting the diversity component and the convergence component to obtain a balance index;
and sorting the population individuals according to the ascending order of the balance index values, selecting a first individual with the minimum population balance index, and selecting a second individual through a roulette strategy.
Optionally, the calculation formula of the convergence component is:
f C (x)=d(r,f(x));
wherein f is C (x) Is a convergence component reflecting the distance between the solution and the POF, r represents an objective function value of a point located closest to the POF, d (r, f (x)) represents the distance between r and f (x), and f (x) is an objective function value vector constituted for all objective functions at the solution x.
Optionally, the calculation formula of the diversity component is:
wherein,is to measure the solution x in the target space relative to f m A diversity component of the position of the axis, v m =(0,...,1 m ,., 0) is an M-dimensional vector, θ (v) m ,f(x)-z * ) Denotes v m And f (x) -z * Angle of (a) z * As a reference point.
Optionally, the expression of the balance index is:
B_fit(x)=η 1 f C (x)+η 2 f D (x);
wherein f is C (x) Is a convergence component reflecting the distance between the solution and the POF, is to measure the solution x in the target space relative to f m A component of the diversity of the position of the axis, η 1 Represents the convergence component f C (x) Weight of, η 2 Representation ofDiversity component f D (x) The weight of (c).
On the other hand, the dynamic workshop scheduling system based on the balance index adaptive evolution is provided and comprises a variable coding module, an operator calculating module and an evolution strategy module; wherein,
the variable coding module is used for carrying out discrete indirect coding on the task to be scheduled;
the operator calculation module is used for traversing the codes to convert the sequences after the discrete indirect codes are finished, and generating new code individuals by adopting operators based on the exchange sequences;
and the evolution strategy module is used for evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on balance indexes, and the evaluation result is used as an index for parent individual selection and local search selection.
According to the technical scheme, compared with the prior art, the invention discloses a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution, which has the following beneficial technical effects:
(1) by designing a discrete indirect variable coding form, the generation of an infeasible solution is avoided, and the solving speed of the algorithm is improved;
(2) and the operator is generated based on the new solution of the exchange sequence, so that the individual can be generated quickly and efficiently. Meanwhile, the algorithm is applied to the scheduling problem under different scenes in a stable effect by combining a self-adaptive evolution strategy based on balance indexes, and the method has good solving speed.
(3) The adaptive search strategy based on the balance index can accelerate algorithm convergence and improve algorithm performance, so that the algorithm has a good solving effect on scheduling problems of different scenes, and 30-50% of running time can be saved in different scenes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a diagram of an example of ordered discrete integer coding of the present invention;
FIG. 3 is a schematic diagram of the exchange sequence algorithm with Pop1 as the implementation object of the present invention;
FIG. 4 is a flow chart of the adaptive strategy based on balance index according to the present invention;
FIG. 5 is a frame diagram of the dynamic scheduling algorithm of the present invention;
fig. 6 is a system configuration diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment 1 of the invention discloses a cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution, which comprises the following specific steps as shown in figure 1:
s1, discrete indirect coding is carried out on the task to be scheduled;
s2, traversing the codes to convert the sequences after finishing the discrete indirect coding, and generating new coding individuals by adopting an operator based on the exchange sequences;
and S3, evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on the balance indexes, and taking the evaluation result as the indexes of parent individual selection and local search selection.
The adaptive evolution strategy based on the balance indexes aims to ensure that the scheduling problem solved by the scheduling algorithm under different scenes has good performance, namely the capability of the algorithm for adapting to dynamic changes of different scenes is improved, and the algorithm is not only used for solving a single scene. S2 shows a new individual generation mode, similar to the cross mutation operation in genetic algorithm, aiming at expanding the algorithm search space to enhance the diversity of population and enhance the search performance of algorithm. Both strategies are operations on solution sets, but the emphasis is different. S3, evaluating the individuals through indexes to obtain solutions with better diversity and convergence, and enhancing the dynamic solving capability of the algorithm to adapt to different scenes; s2 expands the search range of the algorithm by generating a new solution.
In order to avoid the generation of an infeasible solution in the solving process, the searching efficiency of the multi-target evolutionary algorithm is improved. The invention adopts a discrete indirect coding mode, and the coding bits represent the priority when manufacturing resources or computing resources are allocated to tasks. Specifically, when n calculation tasks and m manufacturing tasks are to be scheduled, the coding bit is divided into the manufacturing tasks and the calculation tasks, the lengths of the two sections are n and m respectively, the values of the two sections are positive integers between 0 to (n-1) and 0 to (m-1), and all the positive integers in the value range are covered. FIG. 2 is an example of 5 calculation tasks and manufacturing task encodings.
And after the discrete integer coding of the task to be scheduled is completed, generating a new coding individual by adopting an operator based on the exchange sequence. The pseudo code of the operator in this embodiment is shown in algorithm 1.
Firstly, two parent individuals are selected to be respectively used as an implementation object and a reference object so as to obtain a conversion process sequence from the reference object to the implementation object. Here, Pop1 is an implementation object and Pop2 is a reference object. Traversing the encoded bits in Pop1 and Pop2 results in a sequence of swap pairs that are translated from Pop2 to Pop1 after a lookup comparison. More specifically, for the value of Pop2[ i ], the same coded bit is found in Pop1, the number j of the coded bit in Pop1 is recorded, and then the swap pair (i, j) is stored in the swap pair sequence V. After traversing the two selected individuals, an exchange pair sequence with an indefinite length can be obtained. That is, when the obtained crossover pair sequence is applied to Pop2, Pop1 can be obtained.
The operation process of the exchange sequence method is detailed in fig. 3, and corresponding to the pseudo code, Pop1 and Pop2 are still selected as parent individuals in fig. 3, and are respectively used as an implementation object and a reference object, and the exchange probability is set to 0.5. Traversing the value of each coded bit in the Pop1, searching the position of the coded bit in the Pop2, acquiring exchange pairs such as (2.4), (2.7) and the like with a probability of 0.5, and finally obtaining a sequence of Pop2 to Pop1 exchange pairs. A new individual may be obtained by operating on a certain individual according to the exchange; the exchange pair sequence can also be obtained by limiting the length of the exchange sequence without setting the exchange probability. Because the manufacturing task and the computing task are independent in the coded bits, the manufacturing task coded bits and the computing task coded bits are operated separately in the process of generating a new solution.
Different from a static scheduling task in a single scene, the invention aims at the dynamic scheduling of the cross-domain collaborative distributed workshop, and considers how to keep good solving capability in different scenes after completing coding design and determining a scheduling operator. Therefore, the invention provides a self-adaptive evolution strategy based on balance indexes to adapt to a multi-scene environment.
In the multi-objective evolutionary algorithm, the balance of convergence and diversity is crucial to the performance of the algorithm, in order to improve the speed of the algorithm, an evaluation mechanism based on convergence and diversity index design solution is designed, and the evaluation result is used as an index for parent individual selection and local search selection, namely, the smaller the evaluation value is, the higher the probability of individual selection is. The specific calculation idea is as follows:
the optimization target of a certain dynamic scheduling problem is set as shown in formula (1), and the optimization targets are M in total. Defining convergence index and diversity index and solving the indexes as shown in formulas (2) and (3), f C (x) Is a convergence component reflecting the distance between the solution and the POF (pareto optimum front),is to measure the solution x in the target space relative to f m A diversity component of the position of the axis. As shown in(4) The average value of the diversity components corresponding to the respective targets is used as the diversity index value of the solution x.
min f(x)=min(f 1 (x),f 2 (x),...,f M (x)) (1)
f C (x)=d(r,f(x)) (2)
Wherein r represents a distance above the POF x Objective function values for the nearest points, d (r, f (x)) representing the distance between them, v m =(0,...,1 m ,., 0) is an M-dimensional vector, θ (v) m ,f(x)-z * ) Denotes v m And f (x) -z * Angle of (a) z * As a reference point.
Then the balance of convergence and diversity is defined as shown in equation (5):
B_fit(x)=η 1 f C (x)+η 2 f D (x) (5)
η 1 represents the convergence component f C (x) Weight of, η 2 Representing a representative diversity component f D (x) The weight of (c).
The algorithm thought is specifically as follows, firstly, the diversity component and the convergence component of each individual in the population are respectively calculated by using the formula, and the balance index designed by the invention is obtained by weighting. And then sequencing the population individuals in an increasing order according to the balance index value. And finally, selecting the individual 1 with the minimum current population balance index, and selecting the individual 2 through a roulette strategy. The overall flow is shown in fig. 4.
The adaptive evolution strategy specific pseudo code based on the balance index is as follows:
by combining the above technical solutions, the overall implementation process of the present invention is shown in fig. 5. And after the algorithm initialization is completed, dynamically detecting the current distributed workshop environment. And when the change occurs, dynamically adjusting by adopting a corresponding strategy of uncertainty dynamic environment dynamic. When the environment is not changed, a global search strategy and a local search strategy are combined, a self-adaptive evolution strategy based on balance indexes is adopted in the global search strategy, after the search is finished, objective function value calculation is carried out, the population and pareto front edge solution set are updated, then iteration is repeated, and the output scheduling scheme is quitted after the termination condition is reached. It should be noted that the key points of the present invention are the algorithm initialization coding mode and the adaptive evolution strategy based on the flat index.
the variable coding module is used for carrying out discrete indirect coding on the task to be scheduled;
the operator calculation module is used for traversing the codes to convert the sequences after the discrete indirect codes are finished, and generating new code individuals by adopting operators based on the exchange sequences;
and the evolution strategy module is used for evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on balance indexes, and the evaluation result is used as an index for parent individual selection and local search selection.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution is characterized by comprising the following specific steps:
discrete indirect coding is carried out on the task to be scheduled;
after the discrete indirect coding is completed, traversing the coding by adopting an operator based on an exchange sequence so as to convert the sequence and generate a new coding individual;
and evaluating and constraining the coding individuals by adopting a self-adaptive evolution strategy based on balance indexes, wherein evaluation results are used as indexes of parent individual selection and local search selection.
2. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution according to claim 1, characterized in that the specific process of the discrete indirect coding is as follows: when n calculation tasks and m manufacturing tasks are to be scheduled, the coding bit is divided into the manufacturing tasks and the calculation tasks, the lengths of the two sections are n and m respectively, the values of the two sections are positive integers between 0 to (n-1) and 0 to (m-1), and all the positive integers in the value range are covered.
3. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution of claim 1, wherein the operation process of the exchange sequence is as follows: selecting Pop1 and Pop2 as parent individuals as an implementation object and a reference object respectively, and setting the exchange probability to be 0.5; traversing the numerical value on each coding bit in the Pop1, searching the position in the Pop2, obtaining an exchange pair with the probability of 0.5, finally obtaining an exchange pair sequence from the Pop2 to the Pop1, and operating the individual according to the exchange pair sequence to obtain a new coding individual.
4. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution of claim 1, wherein the adaptive evolution strategy based on balance index is:
respectively calculating the diversity component and the convergence component of each individual in the population;
weighting the diversity component and the convergence component to obtain a balance index;
and sorting the population individuals according to the ascending order of the balance index values, selecting a first individual with the minimum population balance index, and selecting a second individual through a roulette strategy.
5. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution of claim 4, wherein the calculation formula of the convergence component is as follows:
f C (x)=d(r,f(x));
wherein, f C (x) Is a convergence component reflecting the distance between the solution and the POF, r represents an objective function value of a point located closest to the POF, d (r, f (x)) represents the distance between r and f (x), and f (x) is an objective function value vector constituted for all objective functions at the solution x.
6. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution according to claim 4, wherein the calculation formula of the diversity component is as follows:
7. The cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution of claim 4, wherein the expression of the balance index is as follows:
B_fit(x)=η 1 f C (x)+η 2 f D (x);
wherein f is C (x) Is a convergence component reflecting the distance between the solution and the POF, is to measure the solution x in the target space relative to f m A component of the diversity of the position of the axis, η 1 Represents the convergence component f C (x) Weight of, η 2 Represents a representative diversity component f D (x) The weight of (c).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210463887.2A CN114839940A (en) | 2022-04-29 | 2022-04-29 | Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210463887.2A CN114839940A (en) | 2022-04-29 | 2022-04-29 | Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114839940A true CN114839940A (en) | 2022-08-02 |
Family
ID=82568053
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210463887.2A Pending CN114839940A (en) | 2022-04-29 | 2022-04-29 | Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114839940A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116414093A (en) * | 2023-04-13 | 2023-07-11 | 暨南大学 | Workshop production method based on Internet of things system and reinforcement learning |
-
2022
- 2022-04-29 CN CN202210463887.2A patent/CN114839940A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116414093A (en) * | 2023-04-13 | 2023-07-11 | 暨南大学 | Workshop production method based on Internet of things system and reinforcement learning |
CN116414093B (en) * | 2023-04-13 | 2024-01-16 | 暨南大学 | Workshop production method based on Internet of things system and reinforcement learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886589B (en) | Method for solving low-carbon workshop scheduling based on improved whale optimization algorithm | |
CN109948029B (en) | Neural network self-adaptive depth Hash image searching method | |
CN106484512B (en) | The dispatching method of computing unit | |
CN113191484A (en) | Federal learning client intelligent selection method and system based on deep reinforcement learning | |
CN109902873A (en) | A method of the cloud manufacturing resource allocation based on modified whale algorithm | |
CN108075975B (en) | Method and system for determining route transmission path in Internet of things environment | |
CN106610867B (en) | On-chip network task scheduling method and device | |
CN109215344B (en) | Method and system for urban road short-time traffic flow prediction | |
CN113487018A (en) | Global context enhancement graph neural network method based on session recommendation | |
CN114839940A (en) | Cross-domain collaborative workshop dynamic scheduling method based on balance index adaptive evolution | |
CN111832817A (en) | Small world echo state network time sequence prediction method based on MCP penalty function | |
CN110222816B (en) | Deep learning model establishing method, image processing method and device | |
CN110163255B (en) | Data stream clustering method and device based on density peak value | |
CN112036651A (en) | Electricity price prediction method based on quantum immune optimization BP neural network algorithm | |
CN117290721A (en) | Digital twin modeling method, device, equipment and medium | |
CN114708479A (en) | Self-adaptive defense method based on graph structure and characteristics | |
CN112131089B (en) | Software defect prediction method, classifier, computer device and storage medium | |
CN109242190A (en) | Mid-long term load forecasting method and system based on BFGS-FA optimization fractional order gray model | |
CN113191486A (en) | Graph data and parameter data mixed partitioning method based on parameter server architecture | |
CN115169754B (en) | Energy scheduling method and device, electronic equipment and storage medium | |
CN114980216B (en) | Dependency task unloading system and method based on mobile edge calculation | |
CN109347900A (en) | Based on the cloud service system Adaptive evolution method for improving wolf pack algorithm | |
CN115019083A (en) | Word embedding graph neural network fine-grained graph classification method based on few-sample learning | |
CN113111308A (en) | Symbolic regression method and system based on data-driven genetic programming algorithm | |
CN114327853A (en) | Low-cost user association and computation migration method facing complex tasks in cloud-side hybrid system |
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 |