CN113746855A - Data access method of energy industry cloud network and related equipment - Google Patents
Data access method of energy industry cloud network and related equipment Download PDFInfo
- Publication number
- CN113746855A CN113746855A CN202111055833.4A CN202111055833A CN113746855A CN 113746855 A CN113746855 A CN 113746855A CN 202111055833 A CN202111055833 A CN 202111055833A CN 113746855 A CN113746855 A CN 113746855A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- environment
- cloud network
- coding
- 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 67
- 230000002787 reinforcement Effects 0.000 claims description 48
- 230000004927 fusion Effects 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 34
- 230000009471 action Effects 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 14
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 20
- 230000003993 interaction Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 238000005457 optimization Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 6
- 238000013499 data model Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/06—Notations for structuring of protocol data, e.g. abstract syntax notation one [ASN.1]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a data access method of an energy industry cloud network and related equipment.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a data access method of an energy industry cloud network and related equipment.
Background
With the development of science and technology, data processing technology in the industrial internet is continuously improved.
In the field of energy and power, an energy industry cloud network is a specific practice and important carrier of an industrial internet. The energy industry cloud network can receive operation data sent by different types of power equipment in an industrial production field, and data sharing of the equipment operation data among an equipment control field, a supplier side system and a user side is achieved. The operation data sent by different types of power equipment in the industrial production field belong to multi-source heterogeneous data.
However, the energy industry cloud network cannot effectively receive multi-source heterogeneous data.
Disclosure of Invention
In view of the above problems, the present invention provides a data access method for an energy industry cloud network and a related device, which overcome or at least partially solve the above problems, and the technical solutions are as follows:
a data access method of an energy industry cloud network comprises the following steps:
establishing a well-trained data coding model based on a reinforcement learning system structure;
obtaining multi-source heterogeneous data output by at least one industrial field device;
encoding the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
and inputting the multi-source heterogeneous fusion data into the energy industry cloud network.
Optionally, the reinforcement learning architecture includes an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
Optionally, in the process of training the data coding model based on the reinforcement learning architecture, the intelligent agent unit obtains the environmental state S output by the environmental unittAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit carries out normalized coding based on the t, obtains normalized coding information, measures the wide compatibility, the flexible expansibility and the convenient usability of the normalized coding information, and outputs a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1；
The method further comprises the following steps: and circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
A data access apparatus of an energy industry cloud network, comprising: the device comprises a establishing unit, a first obtaining unit, a second obtaining unit and an input unit, wherein:
the establishing unit is used for establishing a data coding model trained on the basis of a reinforcement learning system structure;
the first obtaining unit is used for obtaining multi-source heterogeneous data output by at least one industrial field device;
the second obtaining unit is configured to perform encoding processing on the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
the input unit is used for inputting the multi-source heterogeneous fusion data to the energy industry cloud network.
Optionally, the reinforcement learning architecture includes an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
Optionally, the apparatus further comprises a loop execution unit; wherein:
the intelligent agent unit is used for obtaining the environmental state S output by the environmental unit in the process of training the data coding model based on the reinforcement learning system structuretAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit is used for carrying out standardized coding based on the t, obtaining standardized coding information, measuring the wide compatibility, the flexible expansibility and the convenient usability of the standardized coding information, and outputting a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1；
And the circulating execution unit is used for circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
An electronic device comprising at least one processor, and at least one memory, bus connected with the processor; the processor and the memory complete mutual communication through the bus; the processor is used for calling the program instructions in the memory so as to execute the data access method of the energy industry cloud network.
A computer-readable storage medium, on which a program is stored, which, when executed by a processor, implements the data access method of the energy industry cloud network described above.
According to the data access method and the related equipment of the energy industry cloud network, the multi-source heterogeneous data output by at least one industrial field device is obtained by establishing the data coding model trained on the basis of the reinforcement learning system structure, the multi-source heterogeneous data is coded by using the data coding model to obtain multi-source heterogeneous fusion data, and the multi-source heterogeneous fusion data is input to the energy industry cloud network, so that the energy industry cloud network can effectively access the multi-source heterogeneous data.
The foregoing description is only an overview of the technical solutions of the present invention, and the following detailed description of the present invention is provided to enable the technical means of the present invention to be more clearly understood, and to enable the above and other objects, features, and advantages of the present invention to be more clearly understood.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 shows a flowchart of a data access method of an energy industry cloud network according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the working mechanism of a reinforcement learning algorithm according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a reinforcement learning architecture provided by an embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating a data access device of an energy industry cloud network according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As shown in fig. 1, the present embodiment provides a data access method for an energy industry cloud network, which may include the following steps:
s101, establishing a well-trained data coding model based on a reinforcement learning system structure;
it should be noted that the data access difficulty and the cost are one of the core pain points restricting the application of the industrial internet platform, and the energy industry cloud network, as an application carrier of the industrial internet in the energy industry, has the same problems. Specifically, the data volume is suddenly increased and the data types are diversified, so that the interface specifications of intelligent equipment access in the industrial internet are not uniform, and the modes between protocols are not matched, so that the data transmission is blocked. In order to improve timeliness of the energy industry cloud network and avoid data transmission delay, the invention can provide a data coding model obtained based on reinforcement learning algorithm training, and the data coding model is used for performing effective data compression fusion, redundancy removal and noise reduction on multi-source heterogeneous data and then inputting the data into the energy industry cloud network, so that the energy industry cloud network can realize seamless switching of different data interfaces to adapt to diversified modes of different communication networks, improve data compatibility, and provide better specifications and mechanisms for an electrical equipment intelligent interconnection system and application.
Specifically, the reinforcement learning algorithm may be a machine learning algorithm, and may be a mapping relationship between a learning state and a behavior, so as to maximize data return. As shown in FIG. 2, the reinforcement learning algorithm may include an environment element, a state s, a reinforcement signal r, an intelligent agent element, an action a, and a new state s'.
Optionally, the reinforcement learning architecture includes an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
Specifically, as shown in fig. 3, the present invention can perform functional mapping on the information validity of the data normative sample set, the data normative sample, the multi-source heterogeneous data encoding scheme, and the normative encoding, and the intelligent agent, the action space, the environmental reward, and the environmental state in the reinforcement learning, respectively.
In fig. 3, the intelligent agent unit may include a sample generation policy, and may generate sample 0, sample 1 … …, sample t-2, sample t-1, and sample t.
In fig. 3, the data encoding specification refers to that there are multiple specification modes in the learning process of the data interface specification generation strategy, and there are four tuples in the markov decision process, so as to form a state space, an action space, a state transition probability and a reward value. Specifically, the normalized samples constitute a normalized sample set.
The multi-source heterogeneous data coding scheme may be a coding scheme in the prior art. Specifically, the multi-source heterogeneous data coding scheme can be composed of a standardized data model composed of a basic data model and a professional data model, and the model can be selected according to data transmitted by different data sources, so that preparation is made for forming a uniform data coding form. Specifically, the multi-source heterogeneous data coding scheme may include a power plant identification system, a circuit device code, and the like.
The cross-professional and cross-system unit can realize cross-system and cross-professional data sharing interaction. Specifically, after the external system accesses the model through the interface, the cross-professional cross-system unit can package data submitted by the external system into shared interactive messages to be transmitted in the model, the external system can call the shared interactive services to complete data request services of the external system through the cross-professional cross-system unit, and finally the interface takes out the data in the shared interactive messages to transmit the data to the external system.
The coding unit is the last link of the environment unit and performs unified coding processing on the data transmitted by the previous links, thereby laying a foundation for realizing unified access.
It should be noted that the advantage and essence of the reinforcement learning algorithm in the optimization process can be embodied by combining the reinforcement learning algorithm with the data access process of the energy industry cloud network. In the whole process of training the data coding model by using the reinforcement learning system structure, the reinforcement learning closed loop can be formed by two process steps.
Optionally, in the process of training the data coding model based on the reinforcement learning architecture,the intelligent agent unit obtains the environment state S output by the environment unittAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit carries out normalized coding based on the t, obtains normalized coding information, measures the wide compatibility, the flexible expansibility and the convenient usability of the normalized coding information, and outputs a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1(ii) a At this time, the method may further include: and circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
Specifically, the intelligent agent unit can be based on the environmental status S at the beginning of the whole learning processtAnd a reward value RtAn ambient action t, i.e. a normative sample t, acting on the environment is generated. The environment unit can measure the wide compatibility, flexible expansibility and convenient usability of the normalized coding information internally and generate a current new environment state S according to the measurement resultt+1And returning a reward value Rt+1And finally, according to an optimization principle and an optimization standard formulated by the system, the environment state and the reward value which accord with the precision standard are the multi-source heterogeneous fusion data and are used for forming a related data source of the access platform.
Optionally, the invention can make full use of the reinforcement learning theory to select the data interface specification design with the largest accumulated return. In the learning process of generating the strategy by the data interface specification, the invention can clarify the four-tuple of the Markov decision process corresponding to the task, namely the state space, the action space, the state transition probability and the reward. The present invention can define the accumulated reward of a policy as the following formula (1) and formula (2) when evaluating the policy:
wherein, formula (1) represents the calculation mode of 'T step accumulated reward' in the model learning, and formula (2) represents the calculation mode of 'gamma discount accumulated reward' in the model learning.
And
can represent the cumulative reward brought by using policy pi, starting from state x.
S102, obtaining multi-source heterogeneous data output by at least one industrial field device;
the multi-source heterogeneous data can comprise different types of operation data output by different industrial field devices.
S103, encoding the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
specifically, after the multi-source heterogeneous data is obtained, the data coding model can be used for coding the multi-source heterogeneous data, and the data obtained after coding is determined to be multi-source heterogeneous fusion data.
And S104, inputting the multi-source heterogeneous fusion data to the energy industry cloud network.
Specifically, after multi-source heterogeneous fusion data are obtained, the multi-source heterogeneous fusion data can be input into the energy industry cloud network.
Specifically, the multi-source heterogeneous fusion data are input into the energy industry cloud network, so that the mode matching among protocols can be accelerated, the data transmission delay can be better reduced, the timeliness of the energy industry cloud network is improved, and more importantly, the intelligent seamless switching of different data interfaces to adapt to different network communication modes can be realized.
Optionally, the invention can provide an energy industry cloud network intelligent access system architecture. The architecture may be formed from a first portion, a second portion, and a third portion in that order. The first part can carry out intelligent analysis of a general protocol, and in the first part, the mechanism modeling can be carried out through a machine learning scheme and data through wired and wireless equipment interfaces; performing pattern recognition, and performing intelligent analysis on data by using existing and existing protocols; performing data extraction by using decision matching; and then formatting the data, preprocessing the data, and storing the processed data. The second part can be multi-source heterogeneous data fusion, and a data coding scheme obtained based on reinforcement learning system structure training can be used in the second part; the third part may be a data access architecture, and may include processes such as a coding specification, a general protocol, data fusion, and intelligent optimization.
Specifically, the intelligent analysis and data analysis algorithm is constructed through a lightweight machine learning strategy and a reinforcement learning algorithm, the problems of mismatching of access of various multi-type devices, difficulty in data analysis and low resource utilization rate are effectively solved by using a data sampling strategy, the universality of equipment data access is improved, and the representation codes of different equipment are maximally compatible, so that the correctness of protocol analysis and data analysis is improved, and an application basis is provided for data access of various sensing devices.
It should be noted that, the trend of platform development has been already made by the edge device of the existing industrial internet data access system from "function machine" to "smart machine", which will greatly increase the depth and breadth of edge application. Currently, the intelligence of network devices is mainly focused, and the network devices are further extended to industrial devices in the future. At the present stage, a general processor and a general operating system become a mainstream architecture of an edge gateway, and can support edge industrial requirements such as high-performance motor control, but the real-time and reliability requirements of industrial users are seriously insufficient, the differentiated data fusion aspect is obviously bound by the prior art, a unified data access standard is lacked, and a bottom layer technology and an algorithm guarantee cannot be obtained in a large amount of data sharing and data interaction processes. The invention can solve the problem of difficult data sharing and interaction of cross-professional and cross-system through a standardized modeling data sharing interaction model, designs a data sharing interaction mechanism based on an interface service of a reinforcement learning algorithm, and provides a solution for realizing data sharing and efficient interaction between an equipment intelligent internet of things platform and a supplier side system, so that the capability of receiving and processing multi-source heterogeneous data is greatly enhanced.
According to the data access method of the energy industry cloud network, the multi-source heterogeneous data output by at least one industrial field device is obtained by establishing a data coding model trained based on the reinforcement learning system structure, the multi-source heterogeneous data is coded by using the data coding model to obtain multi-source heterogeneous fusion data, and the multi-source heterogeneous fusion data is input to the energy industry cloud network, so that the energy industry cloud network can effectively access the multi-source heterogeneous data.
Corresponding to the steps shown in fig. 1, as shown in fig. 4, the present embodiment provides a data access apparatus for an energy industry cloud network, where the apparatus may include: a establishing unit 101, a first obtaining unit 102, a second obtaining unit 103 and an input unit 104, wherein:
the establishing unit 101 is configured to establish a data coding model trained based on a reinforcement learning architecture;
it should be noted that the data access difficulty and the cost are one of the core pain points restricting the application of the industrial internet platform, and the energy industry cloud network, as an application carrier of the industrial internet in the energy industry, has the same problems. Specifically, the data volume is suddenly increased and the data types are diversified, so that the interface specifications of intelligent equipment access in the industrial internet are not uniform, and the modes between protocols are not matched, so that the data transmission is blocked. In order to improve timeliness of the energy industry cloud network and avoid data transmission delay, the invention can provide a data coding model obtained based on reinforcement learning algorithm training, and the data coding model is used for performing effective data compression fusion, redundancy removal and noise reduction on multi-source heterogeneous data and then inputting the data into the energy industry cloud network, so that the energy industry cloud network can realize seamless switching of different data interfaces to adapt to diversified modes of different communication networks, improve data compatibility, and provide better specifications and mechanisms for an electrical equipment intelligent interconnection system and application.
Specifically, the reinforcement learning algorithm may be a machine learning algorithm, and may be a mapping relationship between a learning state and a behavior, so as to maximize data return.
Optionally, the reinforcement learning architecture includes an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
Specifically, the invention can respectively carry out functional mapping on the information effectiveness of the data standard sample set, the data standard sample, the multi-source heterogeneous data coding scheme and the standard coding, and the intelligent agent, the action space, the environment reward and the environment state in reinforcement learning.
The intelligent agent unit can include a sample generation strategy, and can generate a sample 0, a sample 1 … …, a sample t-2, a sample t-1 and a sample t.
The data coding specification refers to that in the learning process of the data interface specification generation strategy, various specification modes exist, and a Markov decision process quadruple is commonly used, so that a state space, an action space, a state transition probability and a reward value are formed. Specifically, the normalized samples constitute a normalized sample set.
The multi-source heterogeneous data coding scheme may be a coding scheme in the prior art. Specifically, the multi-source heterogeneous data coding scheme can be composed of a standardized data model composed of a basic data model and a professional data model, and the model can be selected according to data transmitted by different data sources, so that preparation is made for forming a uniform data coding form. Specifically, the multi-source heterogeneous data coding scheme may include a power plant identification system, a circuit device code, and the like.
The cross-professional and cross-system unit can realize cross-system and cross-professional data sharing interaction. Specifically, after the external system accesses the model through the interface, the cross-professional cross-system unit can package data submitted by the external system into shared interactive messages to be transmitted in the model, the external system can call the shared interactive services to complete data request services of the external system through the cross-professional cross-system unit, and finally the interface takes out the data in the shared interactive messages to transmit the data to the external system.
The coding unit is the last link of the environment unit and performs unified coding processing on the data transmitted by the previous links, thereby laying a foundation for realizing unified access.
It should be noted that the advantage and essence of the reinforcement learning algorithm in the optimization process can be embodied by combining the reinforcement learning algorithm with the data access process of the energy industry cloud network. In the whole process of training the data coding model by using the reinforcement learning system structure, the reinforcement learning closed loop can be formed by two processes.
Optionally, the apparatus further comprises a loop execution unit; wherein:
the intelligent agent unit is used for obtaining the environmental state S output by the environmental unit in the process of training the data coding model based on the reinforcement learning system structuretAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit is used for carrying out standardized coding based on the t, obtaining standardized coding information, measuring the wide compatibility, the flexible expansibility and the convenient usability of the standardized coding information, and outputting a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1；
And the circulating execution unit is used for circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
Specifically, the intelligent agent unit can be based on the environmental status S at the beginning of the whole learning processtAnd a reward value RtAn ambient action t, i.e. a normative sample t, acting on the environment is generated. The environment unit can measure the wide compatibility, flexible expansibility and convenient usability of the normalized coding information internally and generate a current new environment state S according to the measurement resultt+1And returning a reward value Rt+1And finally, according to an optimization principle and an optimization standard formulated by the system, the environment state and the reward value which accord with the precision standard are the multi-source heterogeneous fusion data and are used for forming a related data source of the access platform.
Optionally, the invention can make full use of the reinforcement learning theory to select the data interface specification design with the largest accumulated return. In the learning process of generating the strategy by the data interface specification, the invention can clarify the four-tuple of the Markov decision process corresponding to the task, namely the state space, the action space, the state transition probability and the reward. The present invention can define the accumulated reward of a policy as the following formula (1) and formula (2) when evaluating the policy:
wherein, formula (1) represents the calculation mode of 'T step accumulated reward' in the model learning, and formula (2) represents the calculation mode of 'gamma discount accumulated reward' in the model learning.
And
can represent the cumulative reward brought by using policy pi, starting from state x.
The first obtaining unit 102 is configured to obtain multi-source heterogeneous data output by at least one industrial field device;
the multi-source heterogeneous data can comprise different types of operation data output by different industrial field devices.
The second obtaining unit 103 is configured to perform encoding processing on the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
specifically, after the multi-source heterogeneous data is obtained, the data coding model can be used for coding the multi-source heterogeneous data, and the data obtained after coding is determined to be multi-source heterogeneous fusion data.
The input unit 104 is configured to input the multi-source heterogeneous fusion data to the energy industry cloud network.
Specifically, after multi-source heterogeneous fusion data are obtained, the multi-source heterogeneous fusion data can be input into the energy industry cloud network.
Specifically, the multi-source heterogeneous fusion data are input into the energy industry cloud network, so that the mode matching among protocols can be accelerated, the data transmission delay can be better reduced, the timeliness of the energy industry cloud network is improved, and more importantly, the intelligent seamless switching of different data interfaces to adapt to different network communication modes can be realized.
Optionally, the invention can provide an energy industry cloud network intelligent access system architecture. The architecture may be formed from a first portion, a second portion, and a third portion in that order. The first part can carry out intelligent analysis of a general protocol, and in the first part, the mechanism modeling can be carried out through a machine learning scheme and data through wired and wireless equipment interfaces; performing pattern recognition, and performing intelligent analysis on data by using existing and existing protocols; performing data extraction by using decision matching; and then formatting the data, preprocessing the data, and storing the processed data. The second part can be multi-source heterogeneous data fusion, and a data coding scheme obtained based on reinforcement learning system structure training can be used in the second part; the third part may be a data access architecture, and may include processes such as a coding specification, a general protocol, data fusion, and intelligent optimization.
Specifically, the intelligent analysis and data analysis algorithm is constructed through a lightweight machine learning strategy and a reinforcement learning algorithm, the problems of mismatching of access of various multi-type devices, difficulty in data analysis and low resource utilization rate are effectively solved by using a data sampling strategy, the universality of equipment data access is improved, and the representation codes of different equipment are maximally compatible, so that the correctness of protocol analysis and data analysis is improved, and an application basis is provided for data access of various sensing devices.
It should be noted that, the trend of platform development has been already made by the edge device of the existing industrial internet data access system from "function machine" to "smart machine", which will greatly increase the depth and breadth of edge application. Currently, the intelligence of network devices is mainly focused, and the network devices are further extended to industrial devices in the future. At the present stage, a general processor and a general operating system become a mainstream architecture of an edge gateway, and can support edge industrial requirements such as high-performance motor control, but the real-time and reliability requirements of industrial users are seriously insufficient, the differentiated data fusion aspect is obviously bound by the prior art, a unified data access standard is lacked, and a bottom layer technology and an algorithm guarantee cannot be obtained in a large amount of data sharing and data interaction processes. The invention can solve the problem of difficult data sharing and interaction of cross-professional and cross-system through a standardized modeling data sharing interaction model, designs a data sharing interaction mechanism based on an interface service of a reinforcement learning algorithm, and provides a solution for realizing data sharing and efficient interaction between an equipment intelligent internet of things platform and a supplier side system, so that the capability of receiving and processing multi-source heterogeneous data is greatly enhanced.
According to the data access device of the energy industry cloud network, the multi-source heterogeneous data output by at least one industrial field device is obtained by establishing the data coding model trained based on the reinforcement learning system structure, the multi-source heterogeneous data is coded by using the data coding model to obtain multi-source heterogeneous fusion data, the multi-source heterogeneous fusion data is input to the energy industry cloud network, and effective access of the energy industry cloud network to the multi-source heterogeneous data can be achieved.
The data access device of the energy industry cloud network comprises a processor and a memory, wherein the establishing unit, the first obtaining unit, the second obtaining unit, the input unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the data access of the energy industry cloud network is realized by adjusting the kernel parameters.
An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the data access method for the energy industry cloud network.
The embodiment of the invention provides a processor, which is used for running a program, wherein the data access method of the energy industry cloud network is executed when the program runs.
As shown in fig. 5, an embodiment of the present invention provides an electronic device 100, where the electronic device 100 includes at least one processor 200, at least one memory 300 connected to the processor 200, and a bus 400; the processor 200 and the memory 300 complete communication with each other through the bus 400; the processor 200 is configured to call the program instructions in the memory 300 to execute the data access method of the energy industry cloud network. The electronic device in the invention can be a server, a PC, a PAD, a mobile phone and the like.
The invention also provides a computer program product adapted to perform a program for initializing the following method steps when executed on an electronic device:
establishing a well-trained data coding model based on a reinforcement learning system structure;
obtaining multi-source heterogeneous data output by at least one industrial field device;
encoding the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
and inputting the multi-source heterogeneous fusion data into the energy industry cloud network.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, an electronic device includes one or more processors (CPUs), memory, and a bus. The electronic device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present invention, and are not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (8)
1. A data access method of an energy industry cloud network is characterized by comprising the following steps:
establishing a well-trained data coding model based on a reinforcement learning system structure;
obtaining multi-source heterogeneous data output by at least one industrial field device;
encoding the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
and inputting the multi-source heterogeneous fusion data into the energy industry cloud network.
2. The data access method of the energy industry cloud network of claim 1, wherein the reinforcement learning architecture comprises an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
3. The data access method of the energy industry cloud network according to claim 2, wherein the intelligent agent unit obtains the environmental state S output by the environmental unit in the process of training the data coding model based on the reinforcement learning architecturetAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit carries out normalized coding based on the t, obtains normalized coding information, measures the wide compatibility, the flexible expansibility and the convenient usability of the normalized coding information, and outputs a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1；
The method further comprises the following steps: and circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
4. A data access device of an energy industry cloud network, comprising: the device comprises a establishing unit, a first obtaining unit, a second obtaining unit and an input unit, wherein:
the establishing unit is used for establishing a data coding model trained on the basis of a reinforcement learning system structure;
the first obtaining unit is used for obtaining multi-source heterogeneous data output by at least one industrial field device;
the second obtaining unit is configured to perform encoding processing on the multi-source heterogeneous data by using the data encoding model to obtain multi-source heterogeneous fusion data;
the input unit is used for inputting the multi-source heterogeneous fusion data to the energy industry cloud network.
5. The data access device of the energy industry cloud network of claim 4, wherein the reinforcement learning architecture comprises an intelligent agent unit and an environment unit; the intelligent agent unit is a data specification sample set, and the environment unit comprises a data coding specification, a multi-source heterogeneous data coding scheme, a cross-professional cross-system unit and a coding unit.
6. The energy industry cloud network data access apparatus of claim 5, wherein the apparatus further comprises a loop execution unit; wherein:
the intelligent agent unit is used for obtaining the environmental state S output by the environmental unit in the process of training the data coding model based on the reinforcement learning system structuretAnd a prize value RtGenerating an environment action t acting on the environment unit, wherein the t is a standard sample;
the environment unit is used for carrying out standardized coding based on the t, obtaining standardized coding information, measuring the wide compatibility, the flexible expansibility and the convenient usability of the standardized coding information, and outputting a new environment state S to the intelligent agent unit according to the measurement resultt+1And a new prize value Rt+1；
And the circulating execution unit is used for circularly executing the interactive process between the intelligent agent unit and the environment unit until the environment state and the reward value output by the environment unit meet the precision requirement.
7. An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke the program instructions in the memory to perform the data access method of the energy industry cloud network of any of claims 1 to 3.
8. A computer-readable storage medium, on which a program is stored, wherein the program, when executed by a processor, implements the data access method of the energy industry cloud network according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111055833.4A CN113746855A (en) | 2021-09-09 | 2021-09-09 | Data access method of energy industry cloud network and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111055833.4A CN113746855A (en) | 2021-09-09 | 2021-09-09 | Data access method of energy industry cloud network and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113746855A true CN113746855A (en) | 2021-12-03 |
Family
ID=78737733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111055833.4A Pending CN113746855A (en) | 2021-09-09 | 2021-09-09 | Data access method of energy industry cloud network and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113746855A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115567582A (en) * | 2022-11-09 | 2023-01-03 | 山东恒远智能科技有限公司 | Intelligent industrial internet data service system and method |
| CN117032997A (en) * | 2023-10-09 | 2023-11-10 | 深圳云天畅想信息科技有限公司 | Data and computing power resource fusion method, system and computer equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834813A (en) * | 2015-04-28 | 2015-08-12 | 南京邮电大学 | Statistic analysis processing method and device for multi-source heterogeneous data of internet of things |
| US20180260691A1 (en) * | 2017-03-09 | 2018-09-13 | Alphaics Corporation | System and method for training artificial intelligence systems using a sima based processor |
| CN109587519A (en) * | 2018-12-28 | 2019-04-05 | 南京邮电大学 | Heterogeneous network Multipath Video control system and method based on Q study |
| CN110109995A (en) * | 2019-05-14 | 2019-08-09 | 中国矿业大学 | A kind of multi-source heterogeneous data fusion method of fully-mechanized mining working based on deep learning |
| CN110837669A (en) * | 2019-10-25 | 2020-02-25 | 中国地质大学（武汉） | Landslide uncertain model dynamic construction method based on multi-source heterogeneous data fusion |
| CN111897875A (en) * | 2020-07-31 | 2020-11-06 | 平安科技（深圳）有限公司 | Fusion processing method and device for urban multi-source heterogeneous data and computer equipment |
| CN111950627A (en) * | 2020-08-11 | 2020-11-17 | 重庆大学 | Multi-source information fusion method and application thereof |
| CN112069662A (en) * | 2020-08-20 | 2020-12-11 | 北京仿真中心 | Complex product autonomous construction method and module based on man-machine hybrid enhancement |
| CN112287972A (en) * | 2020-09-28 | 2021-01-29 | 清华大学 | Power system power flow adjusting method based on reinforcement learning and multi-source data integration |
| CN112907222A (en) * | 2021-03-25 | 2021-06-04 | 清华大学 | Multi-source heterogeneous power grid operation supervision service data fusion method |
| CN113312428A (en) * | 2021-05-28 | 2021-08-27 | 中国人民解放军战略支援部队航天工程大学 | Multi-source heterogeneous training data fusion method, device and equipment |
-
2021
- 2021-09-09 CN CN202111055833.4A patent/CN113746855A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834813A (en) * | 2015-04-28 | 2015-08-12 | 南京邮电大学 | Statistic analysis processing method and device for multi-source heterogeneous data of internet of things |
| US20180260691A1 (en) * | 2017-03-09 | 2018-09-13 | Alphaics Corporation | System and method for training artificial intelligence systems using a sima based processor |
| CN109587519A (en) * | 2018-12-28 | 2019-04-05 | 南京邮电大学 | Heterogeneous network Multipath Video control system and method based on Q study |
| CN110109995A (en) * | 2019-05-14 | 2019-08-09 | 中国矿业大学 | A kind of multi-source heterogeneous data fusion method of fully-mechanized mining working based on deep learning |
| CN110837669A (en) * | 2019-10-25 | 2020-02-25 | 中国地质大学（武汉） | Landslide uncertain model dynamic construction method based on multi-source heterogeneous data fusion |
| CN111897875A (en) * | 2020-07-31 | 2020-11-06 | 平安科技（深圳）有限公司 | Fusion processing method and device for urban multi-source heterogeneous data and computer equipment |
| CN111950627A (en) * | 2020-08-11 | 2020-11-17 | 重庆大学 | Multi-source information fusion method and application thereof |
| CN112069662A (en) * | 2020-08-20 | 2020-12-11 | 北京仿真中心 | Complex product autonomous construction method and module based on man-machine hybrid enhancement |
| CN112287972A (en) * | 2020-09-28 | 2021-01-29 | 清华大学 | Power system power flow adjusting method based on reinforcement learning and multi-source data integration |
| CN112907222A (en) * | 2021-03-25 | 2021-06-04 | 清华大学 | Multi-source heterogeneous power grid operation supervision service data fusion method |
| CN113312428A (en) * | 2021-05-28 | 2021-08-27 | 中国人民解放军战略支援部队航天工程大学 | Multi-source heterogeneous training data fusion method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 杜威; 丁世飞: "《多智能体强化学习综述》", 《计算机科学》 * |
| 杜威; 丁世飞: "《多智能体强化学习综述》", 《计算机科学》, vol. 46, no. 8, 15 August 2019 (2019-08-15), pages 1 - 8 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115567582A (en) * | 2022-11-09 | 2023-01-03 | 山东恒远智能科技有限公司 | Intelligent industrial internet data service system and method |
| CN115567582B (en) * | 2022-11-09 | 2023-09-15 | 山东恒远智能科技有限公司 | Intelligent industrial Internet data service system and method |
| CN117032997A (en) * | 2023-10-09 | 2023-11-10 | 深圳云天畅想信息科技有限公司 | Data and computing power resource fusion method, system and computer equipment |
| CN117032997B (en) * | 2023-10-09 | 2024-01-26 | 深圳云天畅想信息科技有限公司 | Data and computing power resource fusion method, system and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113746855A (en) | Data access method of energy industry cloud network and related equipment | |
| CN110334436B (en) | Data processing method and device | |
| Tan et al. | Toward a future network architecture for intelligence services: A cyber digital twin-based approach | |
| Liang et al. | Generative AI-driven semantic communication networks: Architecture, technologies and applications | |
| CN112884120A (en) | Graph neural network representation architecture | |
| CN117421398A (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN113485765B (en) | Control strategy configuration method, device, equipment and medium of intelligent equipment of Internet of things | |
| CN118410146A (en) | Cross search method, device, equipment and storage medium based on large language model | |
| CN116860447B (en) | Task caching method, device, system, equipment and medium | |
| CN117709466A (en) | Reasoning method and device based on large language model, electronic equipment and storage medium | |
| CN115994668B (en) | Intelligent community resource management system | |
| CN116913266A (en) | Voice detection method, device, equipment and storage medium | |
| CN116560968A (en) | Simulation calculation time prediction method, system and equipment based on machine learning | |
| CN116186295A (en) | Attention-based knowledge graph link prediction method, attention-based knowledge graph link prediction device, attention-based knowledge graph link prediction equipment and attention-based knowledge graph link prediction medium | |
| CN114979310A (en) | Communication protocol access method, device, equipment and storage medium | |
| CN114490969A (en) | Question and answer method and device based on table and electronic equipment | |
| CN107577536A (en) | Optimizing application method and Related product | |
| CN113111642A (en) | Natural language identification model generation method, natural language processing method and equipment | |
| CN109285559B (en) | Role transition point detection method and device, storage medium and electronic equipment | |
| CN118151983B (en) | Microservice completion method, apparatus, related device and computer program product | |
| CN116527664A (en) | Block chain transaction processing method, device, medium and system | |
| CN113572679B (en) | Account intimacy generation method and device, electronic equipment and storage medium | |
| CN115953559B (en) | Virtual object processing method and device | |
| CN118760528A (en) | Calculation force matching method and system based on artificial intelligence | |
| CN118505326A (en) | Commission amount determining method, apparatus, computer device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211203 |
|
| RJ01 | Rejection of invention patent application after publication |