CN112884247B - Command management and control center and control method - Google Patents

Command management and control center and control method Download PDF

Info

Publication number
CN112884247B
CN112884247B CN202110309325.8A CN202110309325A CN112884247B CN 112884247 B CN112884247 B CN 112884247B CN 202110309325 A CN202110309325 A CN 202110309325A CN 112884247 B CN112884247 B CN 112884247B
Authority
CN
China
Prior art keywords
task
communication
command
task scheduling
base station
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
Application number
CN202110309325.8A
Other languages
Chinese (zh)
Other versions
CN112884247A (en
Inventor
成清
黄金才
程光权
张小可
吴克宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202110309325.8A priority Critical patent/CN112884247B/en
Publication of CN112884247A publication Critical patent/CN112884247A/en
Application granted granted Critical
Publication of CN112884247B publication Critical patent/CN112884247B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • 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
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • 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

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Educational Administration (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention relates to the technical field of command control, and discloses a command management and control center control method, which comprises the following steps: optimizing wireless network communication of the command management and control center area by using a communication area optimization algorithm based on a communication base station; the command management and control center conducts command and dispatch of industrial tasks by utilizing the task flow dispatching model to obtain task dispatching instructions of the industrial tasks; according to the obtained task scheduling instruction, the task scheduling instruction is sent to target equipment by utilizing a dynamic communication strategy; and the target equipment executes the received scheduling task by utilizing the multi-equipment intelligent mobile anti-collision algorithm according to the received task scheduling instruction. The invention also provides a command management and control center. The invention realizes the control of the command management and control center.

Description

Command management and control center and control method
Technical Field
The invention relates to the technical field of command management and control, in particular to a command management and control center and a control method.
Background
In recent years, with the rise of technologies such as the internet, cloud computing and artificial intelligence, the burden and pressure faced by first-line staff in the field of industrial control are lightened, and intelligent command management and control by using the internet and the artificial intelligence technology is a hot topic in the current research field.
At present, the existing industrial command management and control system still adopts a closed system structure, and cannot generate effective intelligent decisions due to poor multi-source information access capability, and can only take a passive execution role in an industrial scene, so that the production requirements of flexibility, agility and customization cannot be met.
In view of this, how to make more intelligent decisions by using the command management and control center becomes a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention provides a command management and control center control method, which optimizes wireless network communication of a command management and control center area by utilizing a communication area optimization algorithm based on a communication base station, conducts command and dispatch of industrial tasks by utilizing a task flow dispatching model, and finally sends task dispatching instructions to target equipment by utilizing a dynamic communication strategy, wherein the target equipment executes received dispatching tasks by utilizing a multi-equipment intelligent mobile anti-collision algorithm under an industrial scene where the target equipment is located according to the received task dispatching instructions.
In order to achieve the above object, the command management center control method provided by the present invention includes:
optimizing wireless network communication of the command management and control center area by using a communication area optimization algorithm based on a communication base station;
the command management and control center conducts command and dispatch of industrial tasks by utilizing the task flow dispatching model to obtain task dispatching instructions of the industrial tasks;
according to the obtained task scheduling instruction, the task scheduling instruction is sent to target equipment by utilizing a dynamic communication strategy;
and the target equipment executes the received scheduling task by utilizing the multi-equipment intelligent mobile anti-collision algorithm according to the received task scheduling instruction.
Optionally, the communication optimization objective function of the command control area of the command control center is:
Figure BDA0002989133580000021
Figure BDA0002989133580000022
x i ＝sigmoid(k 1 (RSRP i -D i ))
y i ＝sigmoid(k 1 (SINR i -D i ))
wherein:
a is the number of sampling points in a command control area;
x i for RSRP coverage of the sampling point i, in a specific embodiment of the present invention, the sigmoid function is a tanh function;
y i for the SINR coverage of the sampling point i, in a specific embodiment of the present invention, the sigmoid function is a tanh function;
c is a similarity constant, which is set to 0.4;
D i the farthest distance between the antenna of the communication base station and the sampling point i is set;
f i representing the communication coverage rate of the sampling point i;
c represents the communication coverage rate of the command control area;
θ＝{θ 1 ,θ 2 ,…,θ n and all adjustable communication base station antenna angles, wherein theta i For the antenna angle of the ith communication base station, in one embodiment of the present invention, the communication base station antenna angle has an angle lower bound
Figure BDA0002989133580000023
Upper boundary of angle
Figure BDA0002989133580000024
Optionally, the optimizing the communication of the command management center area by using a communication area optimization algorithm based on the communication base station includes:
1) Calculating the gradient sum of the communication coverage rate of all sampling points:
Figure BDA0002989133580000025
2) Using gradient descent algorithm pairs based on all sampling points
Figure BDA0002989133580000026
Optimizing, setting the maximum iteration number N based on the gradient descent algorithm of all sampling points, and calculating the gradient ++of each sampling point i>
Figure BDA0002989133580000027
And obtain each sampling point
Figure BDA0002989133580000028
Figure BDA0002989133580000029
Thereby obtaining the following steps:
Figure BDA0002989133580000031
and (3) carrying out decision optimization on theta:
Figure BDA0002989133580000032
wherein:
η is the learning rate based on the gradient descent algorithm of all the sampling points, and is set to 0.2;
3) Repeating the iteration step 3) until the maximum iteration number N of the algorithm is reached, and outputting the antenna angle theta= { theta of the communication base station at the moment 1 ,θ 2 ,…,θ n And the communication base station modifies the antenna angle according to the output antenna angle of the communication base station.
Optionally, the command management and control center performs command and dispatch of the industrial task by using a task flow dispatching model, including:
1) The task flow scheduling model receives a plurality of industrial tasks, generates task scheduling instructions of the industrial tasks, writes the task scheduling instructions into a cache every time when one task scheduling instruction is generated, and completes consumption of the task scheduling instructions if the task scheduling instructions in the cache are sent to industrial equipment;
2) The method comprises the steps of monitoring the number of task scheduling instructions in a cache by using a monitor, and sending data quantity change information in the cache to a cache write-in controller, wherein the cache write-in controller mainly has the function of adjusting the generation speed of the task scheduling instructions according to the cache data consumption rate so as to maintain the number of the task scheduling instructions in the cache to be near a reference capacity;
3) The cache write controller adopts the average value of the consumption period of the historical task scheduling instruction to estimate the production interval of the task scheduling instruction:
Figure BDA0002989133580000033
Figure BDA0002989133580000034
wherein:
Figure BDA0002989133580000035
scheduling a time interval between instruction consumption for the ith and ith-1 th tasks monitored by the monitor;
Figure BDA0002989133580000036
scheduling a production interval estimation value of the instruction for the task;
4) Setting a reference capacity N c So that the number of task scheduling instructions in the cache is maintained near the reference capacity and according to the set reference capacity N c Production interval estimation for task scheduling instructions
Figure BDA0002989133580000037
Adjusting, wherein the production interval estimated value of the adjusted task scheduling instruction is->
Figure BDA0002989133580000038
The method comprises the following steps:
Figure BDA0002989133580000039
wherein:
t is the interpolation period of the task scheduling instruction in the cache;
n is the number of existing task scheduling instructions in the cache.
Optionally, the sending the task scheduling instruction to the target device by using the dynamic communication policy includes:
dividing the generated task scheduling instruction into n data blocks P 1 ～P n Placing it into a window;
selecting a window w by using a probability p, randomly selecting d data blocks from the window w, performing an XOR operation to generate a compressed data packet, and transmitting the compressed data packet to target equipment; setting a communication dynamic service quality threshold T in the compressed data packets, if the number of the transmitted compressed data packets is greater than T, adopting high communication dynamic service quality, otherwise adopting low communication dynamic service quality;
and after receiving the compressed data packets, delivering the compressed data packets to an application layer for decompression processing to obtain a task scheduling instruction.
Optionally, the performing the received scheduling task by using the multi-device intelligent mobile anti-collision algorithm includes:
the multi-device intelligent mobile anti-collision algorithm consists of a multi-device intelligent mobile anti-collision model, wherein the multi-device intelligent mobile anti-collision model adopts two neural network Q value networks and a target network to train industrial equipment, each neural network consists of an input layer, a plurality of hidden layers and an output layer, a full connection mode is adopted between the layers, and relu is used as an activation function;
the intelligent mobile anti-collision algorithm flow of the multi-equipment is as follows:
1) Taking a task scheduling instruction received by target equipment and environment information of the target equipment as input of a multi-equipment intelligent mobile anti-collision model, wherein the environment information of the target equipment comprises the position of the target equipment and the position and action of industrial equipment nearby the target equipment; setting the maximum iteration number as N;
2) The saidThe multi-device intelligent mobile anti-collision model firstly deletes actions possibly causing collision and then deletes action set { a } after collision actions 1 ,a 2 Randomly selecting an action a from … i And calculates a prize value for performing the action:
Figure BDA0002989133580000041
wherein:
R 1 a prize value that is the greatest for the distance traveled toward the target;
R 2 deducting a prize value for the target device whose number of forward actions does not reach a maximum;
u is the maximum number of rounds for which the target device reaches the target position in view of the collision situation;
v is the maximum number of rounds for the target device to reach the target position without considering the collision;
z is taking the current action a i Afterwards, the number of rounds needed;
3) Judging whether the target position is reached, if the target position is not reached, updating the network parameter theta, wherein the objective function of updating the network parameter theta is as follows:
Figure BDA0002989133580000051
wherein:
Figure BDA0002989133580000052
to take action a i A subsequent prize value;
s i to take action a i The location of the back target device;
η represents the learning rate of the algorithm model, and the initial value is 0.2;
4) Repeating the steps 2) -3) until reaching the target position, and outputting the path sequence and the rewarding value at the moment; meanwhile, in a specific embodiment of the present invention, if the difference between the movement strategy ratios of the two movements is too large, a higher learning rate is required, and the calculation formula of the movement strategy ratio r is as follows:
Figure BDA0002989133580000053
wherein:
π θ′ (a i |s i ) Is the latest movement strategy;
π θ (a i |s i ) Is a previous movement strategy;
5) Repeating the steps 2) -4) until the set maximum iteration number N is reached, obtaining N path sequences, and selecting a path with the largest rewarding value as a moving path of the target equipment.
In addition, in order to achieve the above object, the present invention further provides a command management and control center, including:
the wireless network optimizing device is used for optimizing wireless network communication of the command management and control center area by using a communication area optimizing algorithm based on the communication base station;
the task processor is used for commanding and controlling the center to conduct commanding and dispatching of the industrial task by utilizing the task flow dispatching model, obtaining a task dispatching instruction of the industrial task and sending the task dispatching instruction to the target equipment by utilizing the dynamic communication strategy;
and the command management center control device is used for executing the received dispatching task by utilizing the multi-device intelligent mobile anti-collision algorithm according to the received task dispatching instruction.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, on which command center control program instructions are stored, where the command center control program instructions may be executed by one or more processors to implement the steps of the implementation method of command center control as described above.
Compared with the prior art, the invention provides a command management center control method, which has the following advantages:
firstly, the invention provides a communication area optimization algorithm based on a communication base station, which optimizes wireless network communication of a command management and control center area and sets a communication optimization objective function of the command management and control center command and control area:
Figure BDA0002989133580000061
Figure BDA0002989133580000062
x i ＝sigmoid(k 1 (RSRP i -D i ))
y i ＝sigmoid(k 1 (SINR i -D i ))
wherein: a is the number of sampling points in a command control area; x is x i RSRP coverage for sampling point i; y is i SINR coverage for sample point i; c is a similarity constant, which is set to 0.4; d (D) i The farthest distance between the antenna of the communication base station and the sampling point i is set; f (f) i Representing the communication coverage rate of the sampling point i; c represents the communication coverage rate of the command control area; θ= { θ 1 ,θ 2 ,…,θ n And all adjustable communication base station antenna angles, wherein theta i For the antenna angle of the ith communication base station, in one embodiment of the present invention, the communication base station antenna angle has an angle lower bound
Figure BDA0002989133580000063
Upper angle limit->
Figure BDA0002989133580000064
Calculating the gradient sum of the communication coverage rate of all sampling points:
Figure BDA0002989133580000065
based on total recoverySample point gradient descent algorithm pair
Figure BDA00029891335800000611
Optimizing, setting the maximum iteration number N based on the gradient descent algorithm of all sampling points, and calculating the gradient ++of each sampling point i>
Figure BDA0002989133580000066
And get +/for each sampling point>
Figure BDA0002989133580000067
Figure BDA0002989133580000068
Thereby obtaining the following steps:
Figure BDA0002989133580000069
and (3) carrying out decision optimization on theta:
Figure BDA00029891335800000610
wherein: η is the learning rate based on the gradient descent algorithm of all the sampling points, and is set to 0.2; repeating the iteration step 3) until the maximum iteration number N of the algorithm is reached, and outputting the antenna angle theta= { theta of the communication base station at the moment 1 ,θ 2 ,…,θ n And the communication base station modifies the antenna angle according to the output antenna angle of the communication base station, so that the wireless network communication optimization of the command management center area is realized by modifying the antenna angle of the communication base station based on the objective function.
Simultaneously, the industrial task is written into the task scheduling buffer memory according to the sequence of the task progress by utilizing the task flow scheduling model, the task flow scheduling model receives a plurality of industrial tasks and generates task scheduling instructions of the industrial tasks, each task scheduling instruction is written into the buffer memory, and if the task scheduling instructions in the buffer memory are sent to industrial equipment, the consumption of the task scheduling instructions is completed; the method comprises the steps of monitoring the number of task scheduling instructions in a cache by using a monitor, and sending data quantity change information in the cache to a cache write-in controller, wherein the cache write-in controller mainly has the function of adjusting the generation speed of the task scheduling instructions according to the cache data consumption rate so as to maintain the number of the task scheduling instructions in the cache to be near a reference capacity; the cache write controller adopts the average value of the consumption period of the historical task scheduling instruction to estimate the production interval of the task scheduling instruction:
Figure BDA0002989133580000071
wherein:
Figure BDA0002989133580000073
scheduling a time interval between instruction consumption for the ith and ith-1 th tasks monitored by the monitor;
Figure BDA0002989133580000074
scheduling a production interval estimation value of the instruction for the task; setting a reference capacity N c So that the number of task scheduling instructions in the cache is maintained near the reference capacity and according to the set reference capacity N c Production interval estimation value for task scheduling instruction +.>
Figure BDA0002989133580000075
Adjusting, under the condition that consumption speed of the task scheduling instruction is changed drastically, in order to avoid cache overflow caused by instruction production period adjustment follow-up, the production interval estimated value of the adjusted task scheduling instruction is +.>
Figure BDA0002989133580000076
The method comprises the following steps:
Figure BDA0002989133580000077
wherein: t is the interpolation period of the task scheduling instruction in the cache; n is the number of existing task scheduling instructions in the cache.
Since various industrial devices possibly exist in a target scene where the target device is located, collision of the industrial devices possibly occurs when the industrial devices perform mobile work, after receiving a task scheduling instruction, the target device executes the received scheduling task by utilizing a multi-device intelligent mobile anti-collision algorithm, and in the algorithm, the task scheduling instruction received by the target device and environment information where the target device is located are firstly used as input of a multi-device intelligent mobile anti-collision model, and the environment information where the target device is located comprises the position where the target device is located and the positions and actions of the industrial devices nearby the target device; setting the maximum iteration number as N; the multi-device intelligent mobile anti-collision model firstly deletes the actions possibly causing collision and then deletes the actions { a } after the collision actions 1 ,a 2 Randomly selecting an action a from … i And calculates a prize value for performing the action:
Figure BDA0002989133580000078
wherein: r is R 1 A prize value that is the greatest for the distance traveled toward the target; r is R 2 Deducting a prize value for the target device whose number of forward actions does not reach a maximum; u is the maximum number of rounds for which the target device reaches the target position in view of the collision situation; v is the maximum number of rounds for the target device to reach the target position without considering the collision; z is taking the current action a i Afterwards, the number of rounds needed; judging whether the target position is reached, if the target position is not reached, updating the network parameter theta, wherein the objective function of updating the network parameter theta is as follows:
Figure BDA0002989133580000081
wherein:
Figure BDA0002989133580000082
to take action a i A subsequent prize value; s is(s) i To take action a i The location of the back target device; η represents the learning rate of the algorithm model, and the initial value is 0.2; meanwhile, in a specific embodiment of the present invention, if the difference between the movement strategy ratios of the two movements is too large, a higher learning rate is required, and the calculation formula of the movement strategy ratio r is as follows:
Figure BDA0002989133580000083
wherein: pi θ′ (a i |s i ) Is the latest movement strategy; pi θ (a i |s i ) Is a previous movement strategy; and repeatedly executing the steps until the set maximum iteration number N is reached, obtaining N path sequences, and selecting a path with the largest rewarding value as a moving path of the target equipment, thereby avoiding the problem that the industrial equipment may have moving collision during moving work.
Drawings
Fig. 1 is a schematic flow chart of a command management center control method according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of a command management and control center according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The wireless network communication of the command management and control center area is optimized by utilizing a communication area optimization algorithm based on a communication base station, command and dispatch of industrial tasks are conducted by utilizing a task flow dispatching model, finally, a task dispatching instruction is sent to target equipment by utilizing a dynamic communication strategy, and the target equipment executes the received dispatching task by utilizing a multi-equipment intelligent mobile anti-collision algorithm under the industrial scene where the target equipment is located according to the received task dispatching instruction. Referring to fig. 1, a schematic diagram of a command management center control method according to an embodiment of the present invention is shown.
In this embodiment, the command management center control method includes:
s1, optimizing wireless network communication of a command management and control center area by using a communication area optimization algorithm based on a communication base station.
Firstly, optimizing wireless network communication of a command control center area by using a communication area optimization algorithm based on a communication base station, wherein the command control center command control area is a whole industrial field, and the command control center controls all industrial equipment in the industrial field by sending task scheduling instructions, including starting, specific operation, closing and the like of the industrial equipment;
the communication area optimization algorithm flow based on the communication base station is as follows:
1) Setting a communication optimization objective function of a command control area of a command management and control center:
Figure BDA0002989133580000091
Figure BDA0002989133580000092
x i ＝sigmoid(k 1 (RSRP i -D i ))
y i ＝sigmoid(k 1 (SINR i -D i ))
wherein:
a is the number of sampling points in a command control area;
x i for RSRP coverage of the sampling point i, in a specific embodiment of the present invention, the sigmoid function is a tanh function;
y i for the SINR coverage of the sampling point i, in a specific embodiment of the present invention, the sigmoid function is a tanh function;
c is a similarity constant, which is set to 0.4;
D i the farthest distance between the antenna of the communication base station and the sampling point i is set;
f i representing the communication coverage rate of the sampling point i;
c represents the communication coverage rate of the command control area;
θ＝{θ 1 ,θ 2 ,…,θ n and all adjustable communication base station antenna angles, wherein theta i For the antenna angle of the ith communication base station, in one embodiment of the present invention, the communication base station antenna angle has an angle lower bound
Figure BDA0002989133580000093
Upper boundary of angle
Figure BDA0002989133580000094
2) Calculating the gradient sum of the communication coverage rate of all sampling points:
Figure BDA0002989133580000095
3) Using gradient descent algorithm pairs based on all sampling points
Figure BDA0002989133580000096
Optimizing, setting the maximum iteration number N based on the gradient descent algorithm of all sampling points, and calculating the gradient ++of each sampling point i>
Figure BDA0002989133580000101
And obtain each sampling point
Figure BDA0002989133580000102
Figure BDA0002989133580000103
Thereby obtaining the following steps:
Figure BDA0002989133580000104
and (3) carrying out decision optimization on theta:
Figure BDA0002989133580000105
wherein:
η is the learning rate based on the gradient descent algorithm of all the sampling points, and is set to 0.2;
4) Repeating the iteration step 3) until the maximum iteration number N of the algorithm is reached, and outputting the antenna angle theta= { theta of the communication base station at the moment 1 ,θ 2 ,…,θ n And the communication base station modifies the antenna angle according to the output antenna angle of the communication base station.
S2, the command management and control center conducts command and dispatch of the industrial task by utilizing the task flow dispatching model, and a task dispatching instruction of the industrial task is obtained.
Further, the command management and control center writes the industrial tasks into a task scheduling buffer according to the sequence of task processes by utilizing a task flow scheduling model according to the industrial task arrangement of the industrial site, wherein the industrial tasks comprise the starting, working, moving and stopping of industrial equipment;
the workflow of the task flow scheduling model is as follows:
1) The task flow scheduling model receives a plurality of industrial tasks, generates task scheduling instructions of the industrial tasks, writes the task scheduling instructions into a cache every time when one task scheduling instruction is generated, and completes consumption of the task scheduling instructions if the task scheduling instructions in the cache are sent to industrial equipment;
2) The method comprises the steps of monitoring the number of task scheduling instructions in a cache by using a monitor, and sending data quantity change information in the cache to a cache write-in controller, wherein the cache write-in controller mainly has the function of adjusting the generation speed of the task scheduling instructions according to the cache data consumption rate so as to maintain the number of the task scheduling instructions in the cache to be near a reference capacity;
3) The cache write controller adopts the average value of the consumption period of the historical task scheduling instruction to estimate the production interval of the task scheduling instruction:
Figure BDA0002989133580000106
Figure BDA0002989133580000107
wherein:
Figure BDA0002989133580000111
scheduling a time interval between instruction consumption for the ith and ith-1 th tasks monitored by the monitor;
Figure BDA0002989133580000112
scheduling a production interval estimation value of the instruction for the task;
4) Setting a reference capacity N c So that the number of task scheduling instructions in the cache is maintained near the reference capacity and according to the set reference capacity N c Production interval estimation for task scheduling instructions
Figure BDA0002989133580000113
Adjusting, wherein the production interval estimated value of the adjusted task scheduling instruction is->
Figure BDA0002989133580000114
The method comprises the following steps:
Figure BDA0002989133580000115
wherein:
t is the interpolation period of the task scheduling instruction in the cache;
n is the number of existing task scheduling instructions in the cache.
And S3, sending the task scheduling instruction to the target equipment by utilizing a dynamic communication strategy according to the obtained task scheduling instruction.
Further, according to the obtained task scheduling instruction, the task scheduling instruction is sent to the target device by using a dynamic communication strategy, and the task scheduling flow of the dynamic communication strategy is as follows:
dividing the generated task scheduling instruction into n data blocks P 1 ～P n Placing it into a window;
selecting a window w by using a probability p, randomly selecting d data blocks from the window w, performing an XOR operation to generate a compressed data packet, and transmitting the compressed data packet to target equipment; setting a communication dynamic service quality threshold T in the compressed data packets, if the number of the transmitted compressed data packets is greater than T, adopting high communication dynamic service quality, otherwise adopting low communication dynamic service quality;
and after receiving the compressed data packets, delivering the compressed data packets to an application layer for decompression processing to obtain a task scheduling instruction.
And S4, the target equipment executes the received dispatching task by utilizing a multi-equipment intelligent mobile anti-collision algorithm according to the received task dispatching instruction.
Further, as various industrial devices possibly exist in a target scene where the target device is located, collision of the industrial devices possibly occurs when the industrial devices perform mobile work, after receiving a task scheduling instruction, the target device executes the received scheduling task by utilizing a multi-device intelligent mobile anti-collision algorithm, wherein the scheduling task comprises starting, moving, operating and closing of the industrial devices;
in a specific embodiment of the invention, the multi-device intelligent mobile anti-collision algorithm consists of a multi-device intelligent mobile anti-collision model, the multi-device intelligent mobile anti-collision model trains industrial equipment by adopting two neural network Q value networks and target networks, each neural network consists of an input layer, a plurality of hidden layers and an output layer, a full connection mode is adopted between the layers, and relu is used as an activation function;
the intelligent mobile anti-collision algorithm flow of the multi-equipment is as follows:
1) Taking a task scheduling instruction received by target equipment and environment information of the target equipment as input of a multi-equipment intelligent mobile anti-collision model, wherein the environment information of the target equipment comprises the position of the target equipment and the position and action of industrial equipment nearby the target equipment; setting the maximum iteration number as N;
2) The multi-device intelligent mobile anti-collision model firstly deletes the actions possibly causing collision and then deletes the actions { a } after the collision actions 1 ,a 2 Randomly selecting an action a from … i And calculates a prize value for performing the action:
Figure BDA0002989133580000121
wherein:
R 1 a prize value that is the greatest for the distance traveled toward the target;
R 2 deducting a prize value for the target device whose number of forward actions does not reach a maximum;
u is the maximum number of rounds for which the target device reaches the target position in view of the collision situation;
v is the maximum number of rounds for the target device to reach the target position without considering the collision;
z is taking the current action a i Afterwards, the number of rounds needed;
3) Judging whether the target position is reached, if the target position is not reached, updating the network parameter theta, wherein the objective function of updating the network parameter theta is as follows:
Figure BDA0002989133580000122
wherein:
Figure BDA0002989133580000123
to take action a i A subsequent prize value;
s i to take action a i The location of the back target device;
η represents the learning rate of the algorithm model, and the initial value is 0.2;
4) Repeating the steps 2) -3) until reaching the target position, and outputting the path sequence and the rewarding value at the moment; meanwhile, in a specific embodiment of the present invention, if the difference between the movement strategy ratios of the two movements is too large, a higher learning rate is required, and the calculation formula of the movement strategy ratio r is as follows:
Figure BDA0002989133580000124
wherein:
π θ′ (a i |s i ) Is the latest movement strategy;
π θ (a i |s i ) Is a previous movement strategy;
5) Repeating the steps 2) -4) until the set maximum iteration number N is reached, obtaining N path sequences, and selecting a path with the largest rewarding value as a moving path of the target equipment.
The following describes embodiments of the present invention through an algorithm experiment, and tests were conducted on the inventive treatment method. The hardware testing environment of the algorithm of the invention is: inter (R) Core (TM) i7-6700K CPU, software Matlab2018a; the comparison method is a command management and control center control method based on a genetic algorithm and a command management and control center control method based on SVM.
In the algorithm experiment of the invention, the data set is a command management and control center control command of 10G. The experiment inputs the control instruction into the control method of the command management and control center, and the control accuracy of the command management and control center is used as an evaluation index of algorithm feasibility.
According to experimental results, the control accuracy of the command management center control method based on the genetic algorithm is 87.11%, the control accuracy of the command management center control method based on the neural network is 84.38%, and the control accuracy of the method is 89.97%, compared with a comparison algorithm, the command management center control method provided by the invention can realize more accurate industrial control.
The invention also provides a command management and control center. Referring to fig. 2, an internal structure diagram of a command management center according to an embodiment of the invention is shown.
In this embodiment, the command and control center 1 at least includes a wireless network optimization device 11, a task processor 12, a command and control center control device 13, a communication bus 14, and a network interface 15.
The wireless network optimization device 11 may be a PC (Personal Computer ), a terminal device such as a smart phone, a tablet computer, or a portable computer, or a server.
The task processor 12 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The task processor 12 may in some embodiments be an internal memory unit of the command management center 1, for example a hard disk of the command management center 1. The task processor 12 may also be an external storage device of the command management center 1 in other embodiments, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the command management center 1. Further, the task processor 12 may also include both an internal storage unit and an external storage device of the command management center 1. The task processor 12 may be used not only to store application software and various types of data installed in the command management center 1, but also to temporarily store data that has been output or is to be output.
The command center control device 13 may be, in some embodiments, a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor or other data processing chip for executing program code or processing data stored in the task processor 12, such as command center control program instructions, etc.
The communication bus 14 is used to enable connected communication between these components.
The network interface 15 may optionally comprise a standard wired interface, a wireless interface (e.g. WI-FI interface), typically used to establish a communication connection between the command and control center 1 and other electronic devices.
Optionally, the command management center 1 may further include a user interface, which may include a Display (Display), an input unit such as a Keyboard (Keyboard), and an optional user interface may further include a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or a display unit, as appropriate, for displaying information processed in the command control center 1 and for displaying a visual user interface.
Fig. 2 shows only the command and control center 1 with the assemblies 11-15, and it will be understood by those skilled in the art that the configuration shown in fig. 1 is not limiting of the command and control center 1 and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
In the embodiment of the command and control center 1 shown in fig. 2, command and control center control program instructions are stored in the task processor 12; the command management center control device 13 executes the command management center control program stored in the task processor 12 in the same manner as the command management center control method, and is not described here.
In addition, the embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with command management center control program instructions, and the command management center control program instructions can be executed by one or more processors to realize the following operations:
optimizing wireless network communication of the command management and control center area by using a communication area optimization algorithm based on a communication base station;
the command management and control center conducts command and dispatch of industrial tasks by utilizing the task flow dispatching model to obtain task dispatching instructions of the industrial tasks;
according to the obtained task scheduling instruction, the task scheduling instruction is sent to target equipment by utilizing a dynamic communication strategy;
and the target equipment executes the received scheduling task by utilizing the multi-equipment intelligent mobile anti-collision algorithm according to the received task scheduling instruction.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims (6)

1. The command management center control method is characterized by comprising the following steps:
optimizing wireless network communication of the command management and control center area by using a communication area optimization algorithm based on a communication base station;
the command management and control center conducts command and dispatch of industrial tasks by utilizing the task flow dispatching model to obtain task dispatching instructions of the industrial tasks;
according to the obtained task scheduling instruction, the task scheduling instruction is sent to target equipment by utilizing a dynamic communication strategy;
the target device executes the received scheduling task by utilizing a multi-device intelligent mobile anti-collision algorithm according to the received task scheduling instruction;
the communication optimization objective function of the command control area of the command control center is as follows:
Figure QLYQS_1
Figure QLYQS_2
x i ＝sigmoid(k 1 (RSRP i -D i ))
y i ＝sigmoid(k 1 (SINR i -D i ))
wherein:
a is the number of sampling points in a command control area;
x i RSRP coverage for sampling point i;
y i SINR coverage for sample point i;
c is a similarity constant, which is set to 0.4;
D i the farthest distance between the antenna of the communication base station and the sampling point i is set;
f i representing the communication coverage rate of the sampling point i;
c represents the communication coverage rate of the command control area;
θ＝{θ 1 ，θ 2 ，...，θ n and all adjustable communication base station antenna angles, wherein theta i An antenna angle for the ith communication base station;
the communication of the command management and control center area is optimized by using a communication area optimization algorithm based on a communication base station, and the method comprises the following steps:
1) Calculating the gradient sum of the communication coverage rate of all sampling points:
Figure QLYQS_3
2) Using gradient descent algorithm pairs based on all sampling points
Figure QLYQS_4
Optimizing, setting the maximum iteration number N based on the gradient descent algorithm of all sampling points, and calculating the gradient ++of each sampling point i>
Figure QLYQS_5
Opening to obtain +.>
Figure QLYQS_6
Figure QLYQS_7
Thereby obtaining the following steps:
Figure QLYQS_8
and (3) carrying out decision optimization on theta:
Figure QLYQS_9
wherein:
η is the learning rate based on the gradient descent algorithm of all the sampling points, and is set to 0.2;
3) Repeating the iteration step 3) until the maximum iteration number N of the algorithm is reached, and outputting the antenna angle theta= { theta of the communication base station at the moment 1 ，θ 2 ，...，θ n And the communication base station modifies the antenna angle according to the output antenna angle of the communication base station.
2. The command and control center control method according to claim 1, wherein the command and control center performs command and control of industrial tasks using a task flow scheduling model, comprising:
1) The task flow scheduling model receives a plurality of industrial tasks, generates task scheduling instructions of the industrial tasks, writes the task scheduling instructions into a cache every time when one task scheduling instruction is generated, and completes consumption of the task scheduling instructions if the task scheduling instructions in the cache are sent to industrial equipment;
2) Monitoring the task scheduling instruction quantity in the cache by using a monitor, and sending the data quantity change information in the cache to a cache write-in controller;
3) The cache write controller adopts the average value of the consumption period of the historical task scheduling instruction to estimate the production interval of the task scheduling instruction:
Figure QLYQS_10
Figure QLYQS_11
wherein:
Figure QLYQS_12
scheduling a time interval between instruction consumption for the ith and ith-1 th tasks monitored by the monitor;
Figure QLYQS_13
scheduling a production interval estimation value of the instruction for the task;
4) Setting a reference capacity N c So that the number of task scheduling instructions in the cache is maintained near the reference capacity and according to the set reference capacity N c Production interval estimation for task scheduling instructions
Figure QLYQS_14
Adjusting, wherein the production interval estimated value of the adjusted task scheduling instruction is->
Figure QLYQS_15
The method comprises the following steps:
Figure QLYQS_16
wherein:
t is the interpolation period of the task scheduling instruction in the cache;
n is the number of existing task scheduling instructions in the cache.
3. The command management center control method according to claim 2, wherein the sending the task scheduling instruction to the target device using the dynamic communication policy includes:
dividing the generated task scheduling instruction into n data blocks P 1 ～P n Placing it into a window;
selecting a window w by using a probability p, randomly selecting d data blocks from the window w, performing an XOR operation to generate a compressed data packet, and transmitting the compressed data packet to target equipment; setting a communication dynamic service quality threshold T in the compressed data packets, if the number of the transmitted compressed data packets is greater than T, adopting high communication dynamic service quality, otherwise adopting low communication dynamic service quality;
and after receiving the compressed data packets, delivering the compressed data packets to an application layer for decompression processing to obtain a task scheduling instruction.
4. The command and control center control method according to claim 3, wherein the performing the received scheduling task using a multi-device smart mobile anti-collision algorithm comprises:
the intelligent mobile anti-collision algorithm flow of the multi-equipment is as follows:
1) Taking a task scheduling instruction received by target equipment and environment information of the target equipment as input of a multi-equipment intelligent mobile anti-collision model; setting the maximum iteration number as N;
2) The multi-device intelligent mobile anti-collision model firstly deletes the actions possibly causing collision and then deletes the actions { a } after the collision actions 1 ，a 2 ,. random selection of an action a } i And calculates a prize value for performing the action:
Figure QLYQS_17
wherein:
R 1 a prize value that is the greatest for the distance traveled toward the target;
R 2 for the purpose ofThe number of forward actions of the marking device does not reach the maximum deduction rewards value;
u is the maximum number of rounds for which the target device reaches the target position in view of the collision situation;
v is the maximum number of rounds for the target device to reach the target position without considering the collision;
z is taking the current action a i Afterwards, the number of rounds needed;
3) Judging whether the target position is reached, if the target position is not reached, updating the network parameter theta, wherein the objective function of updating the network parameter theta is as follows:
Figure QLYQS_18
wherein:
Figure QLYQS_19
to take action a i A subsequent prize value;
s i to take action a i The location of the back target device;
η represents the learning rate of the algorithm model, and the initial value is 0.2;
4) Repeating the steps 2) -3) until reaching the target position, and outputting the path sequence and the rewarding value at the moment;
5) Repeating the steps 2) -4) until the set maximum iteration number N is reached, obtaining N path sequences, and selecting a path with the largest rewarding value as a moving path of the target equipment.
5. A command management and control center, characterized in that the command management and control center comprises:
the wireless network optimizing device is used for optimizing wireless network communication of the command management and control center area by using a communication area optimizing algorithm based on the communication base station;
the task processor is used for commanding and controlling the center to conduct commanding and dispatching of the industrial task by utilizing the task flow dispatching model, obtaining a task dispatching instruction of the industrial task and sending the task dispatching instruction to the target equipment by utilizing the dynamic communication strategy;
the command management center control device is used for executing the received dispatching task by utilizing a multi-device intelligent mobile anti-collision algorithm according to the received task dispatching instruction;
the communication optimization objective function of the command control area of the command control center is as follows:
Figure QLYQS_20
Figure QLYQS_21
x i ＝sigmoid(k 1 (RSRP i -D i ))
y i ＝sigmoid(k 1 (SINR i -D i ))
wherein:
a is the number of sampling points in a command control area;
x i RSRP coverage for sampling point i;
y i SINR coverage for sample point i;
c is a similarity constant, which is set to 0.4;
D i the farthest distance between the antenna of the communication base station and the sampling point i is set;
f i representing the communication coverage rate of the sampling point i;
c represents the communication coverage rate of the command control area;
θ＝{θ 1 ，θ 2 ，...，θ n and all adjustable communication base station antenna angles, wherein theta i An antenna angle for the ith communication base station;
the communication of the command management and control center area is optimized by using a communication area optimization algorithm based on a communication base station, and the method comprises the following steps:
1) Calculating the gradient sum of the communication coverage rate of all sampling points:
Figure QLYQS_22
2) Using gradient descent algorithm pairs based on all sampling points
Figure QLYQS_23
Optimizing, setting the maximum iteration number N based on the gradient descent algorithm of all sampling points, and calculating the gradient ++of each sampling point i>
Figure QLYQS_24
Opening to obtain +.>
Figure QLYQS_25
Figure QLYQS_26
Thereby obtaining the following steps:
Figure QLYQS_27
and (3) carrying out decision optimization on theta:
Figure QLYQS_28
wherein:
η is the learning rate based on the gradient descent algorithm of all the sampling points, and is set to 0.2;
3) Repeating the iteration step 3) until the maximum iteration number N of the algorithm is reached, and outputting the antenna angle theta= { theta of the communication base station at the moment 1 ，θ 2 ，...，θ n And the communication base station modifies the antenna angle according to the output antenna angle of the communication base station.
6. A computer readable storage medium having stored thereon command center control program instructions executable by one or more processors to implement the steps of the command center control method of any of claims 1 to 4.
CN202110309325.8A 2021-03-23 2021-03-23 Command management and control center and control method Active CN112884247B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110309325.8A CN112884247B (en) 2021-03-23 2021-03-23 Command management and control center and control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110309325.8A CN112884247B (en) 2021-03-23 2021-03-23 Command management and control center and control method

Publications (2)

Publication Number Publication Date
CN112884247A CN112884247A (en) 2021-06-01
CN112884247B true CN112884247B (en) 2023-07-14

Family

ID=76041913

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110309325.8A Active CN112884247B (en) 2021-03-23 2021-03-23 Command management and control center and control method

Country Status (1)

Country Link
CN (1) CN112884247B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106936892A (en) * 2017-01-09 2017-07-07 北京邮电大学 A kind of self-organizing cloud multi-to-multi computation migration method and system
CN109561148A (en) * 2018-11-30 2019-04-02 湘潭大学 Distributed task dispatching method in edge calculations network based on directed acyclic graph
CN111984426A (en) * 2020-10-09 2020-11-24 中国平安人寿保险股份有限公司 Task scheduling method and device, electronic equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106936892A (en) * 2017-01-09 2017-07-07 北京邮电大学 A kind of self-organizing cloud multi-to-multi computation migration method and system
CN109561148A (en) * 2018-11-30 2019-04-02 湘潭大学 Distributed task dispatching method in edge calculations network based on directed acyclic graph
CN111984426A (en) * 2020-10-09 2020-11-24 中国平安人寿保险股份有限公司 Task scheduling method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN112884247A (en) 2021-06-01

Similar Documents

Publication Publication Date Title
CN110955242B (en) Robot navigation method, system, robot and storage medium
CN110520868A (en) Distributed Reinforcement Learning
JP2020042837A (en) Asynchronous deep reinforcement learning
CN110276439A (en) Time Series Forecasting Methods, device and storage medium based on attention mechanism
CN107443373A (en) Collision prevention method for planning track and device based on articulated arm robots
US20200034747A1 (en) System and method for distributed learning
CN113467952A (en) Distributed federated learning collaborative computing method and system
Jia et al. Review of reinforcement learning research
CN109983480A (en) Use cluster loss training neural network
KR20190043419A (en) Method of controlling computing operations based on early-stop in deep neural network
US20230367934A1 (en) Method and apparatus for constructing vehicle dynamics model and method and apparatus for predicting vehicle state information
CN115330556B (en) Training method, device and product of information adjustment model of charging station
US20210056459A1 (en) Virtual intelligence and optimization through multi-source, real-time, and context-aware real-world data
CA3162812A1 (en) System and method for risk sensitive reinforcement learning architecture
CN111832876A (en) Vehicle scheduling method, readable storage medium and electronic device
CN115239508A (en) Scene planning adjustment method, device, equipment and medium based on artificial intelligence
CN112884247B (en) Command management and control center and control method
Mu et al. Deep reinforcement learning based adaptive threshold multi-tasks offloading approach in mec
CN113110101B (en) Production line mobile robot gathering type recovery and warehousing simulation method and system
CN109981372A (en) Streaming big data processing method and system based on edge calculations
Wang et al. Inverse reinforcement learning with graph neural networks for iot resource allocation
CN115577755A (en) Robot posture correction method, apparatus, computer device, and storage medium
US20220012585A1 (en) Deep reinforcement learning with short-term adjustments
CN114663982A (en) Human hand trajectory prediction and intention recognition method based on multi-feature fusion
WO2022099526A1 (en) Method for training lane change prediction regression model, and lane change predicton method and apparatus

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