CN113283695A - Power dispatching intelligent agent implementation method and system based on artificial intelligence - Google Patents
Power dispatching intelligent agent implementation method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN113283695A CN113283695A CN202110420336.3A CN202110420336A CN113283695A CN 113283695 A CN113283695 A CN 113283695A CN 202110420336 A CN202110420336 A CN 202110420336A CN 113283695 A CN113283695 A CN 113283695A
- Authority
- CN
- China
- Prior art keywords
- dispatcher
- scheduling
- voice
- identity
- dispatching
- 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 60
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 230000001815 facial effect Effects 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims 2
- 239000002994 raw material Substances 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000003795 chemical substances by application Substances 0.000 description 17
- 238000011176 pooling Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000003860 storage Methods 0.000 description 6
- 230000004913 activation Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003631 expected effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06Q10/06—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Audiology, Speech & Language Pathology (AREA)
Abstract
The invention discloses an artificial intelligence-based power dispatching intelligent agent implementation method and system, which comprises the steps that after a voice recognition module receives a dispatching instruction of a superior dispatcher, the identity of the superior dispatcher is confirmed through a voice recognition module and a face recognition module, and if the identity is correct, the operation data of a power system and a dispatching scheme of a knowledge base module are obtained; according to the operation data, the load flow calculation and safety check are carried out through the load flow calculation and safety check module, and whether the scheduling scheme of the knowledge base module meets the safety check requirement is judged; if the voice identity is matched with the voice identity, sending a dispatching instruction to a lower-level dispatcher, and confirming the voice identity and the voice information of the dispatching instruction of the lower-level dispatcher through a voice recognition module; if the identity of the subordinate dispatcher is correct, judging the rule of the dispatching instruction; the invention improves the safety of the scheduling process by the voice recognition and image recognition technology; meanwhile, artificial intelligence is applied to power system scheduling, and intelligent power system scheduling is achieved.
Description
Technical Field
The invention relates to the technical field of power dispatching, in particular to a power dispatching intelligent agent implementation method and system based on artificial intelligence.
Background
The power industry plays an important role in energy support and assistance in daily production and life, along with the continuous improvement of social economy on power demand in rapid development, the development of renewable energy, distributed power generation and the like promotes the rapid expansion of the scale of a power grid, the difficulty of management, scheduling and maintenance of a traditional centralized power system is obviously increased, and the requirements on information-based and intelligent management and scheduling of the power grid are continuously improved.
At present, the power grid regulation and control business still mainly takes equipment monitoring and manual analysis as main services, regulation and control personnel dominate decision-making, execution and other links, the power dispatching accuracy depends more on the experience analysis capability of the regulation and control personnel, and the requirement of intelligent dispatching cannot be met. The current power grid operation scheduling mode is gradually complicated, and the traditional regulation and control method based on mechanism analysis and a power grid model is difficult to achieve the expected effect when the problems of nonlinearity, discontinuity and prediction uncertainty of a large power grid are solved.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides an artificial intelligence-based power dispatching intelligent agent implementation method, which can solve the problem that the conventional power dispatching system is difficult to achieve the expected effect when processing the problems of large power grid nonlinearity, discontinuity and prediction uncertainty.
In order to solve the technical problems, the invention provides the following technical scheme: after a voice recognition module receives a dispatching instruction of a superior dispatcher, the identity of the superior dispatcher is confirmed through the voice recognition module and a face recognition module, and if the identity of the superior dispatcher is correct, operation data of a power system and a dispatching scheme of a knowledge base module are acquired; otherwise, the identity of the superior dispatcher is confirmed again; according to the operation data, load flow calculation and safety check are carried out through a load flow calculation and safety check module, and whether the scheduling scheme of the knowledge base module meets the safety check requirement of the power system or not is judged; if the requirement is met, sending a scheduling instruction to a lower-level dispatcher; otherwise, the scheduling scheme is obtained again; confirming the voice identity information and the scheduling instruction voice information of the subordinate dispatcher through a voice recognition module; if the identity of the subordinate dispatcher is correct, judging the rule of the dispatching instruction; otherwise, performing dispatcher identity abnormity feedback; if the rule is not in accordance with the scheduling instruction, feedback is carried out when the rule is not in accordance with the scheduling rule; otherwise, the lower-level dispatcher repeats the dispatching instruction to the upper-level dispatcher.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation method of the present invention, wherein: if the superior dispatcher confirms that the dispatching instruction is correct, the subordinate dispatcher executes the dispatching instruction; and if the superior dispatcher does not confirm the dispatching instruction, feeding back the unconfirmed dispatching instruction to the superior dispatcher.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation method of the present invention, wherein: the voice recognition module collects voice information of the superior dispatcher and recognizes the dispatching instruction by using a voice recognition chip, and performs voice information matching on the superior dispatcher by combining a voice recognition algorithm according to the voice information and a built voice library; the face recognition module collects face information of a superior dispatcher by using a camera and performs face information matching on the superior dispatcher in a constructed image library by using a face recognition algorithm.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation method of the present invention, wherein: the constructed voice library and the image library comprise voice data mining is carried out on the recording data in the process of maintenance in the past year by utilizing a deep learning algorithm, and the voice characteristics of power grid dispatching personnel, namely the voice library, are obtained; the image library: and learning the image information of the power grid dispatching personnel by using a deep learning algorithm to obtain the facial features of the power grid dispatching personnel, namely the image library.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation method of the present invention, wherein: the scheduling scheme includes scheduling experience of a scheduling expert and an existing scheduling scheme.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation method of the present invention, wherein: the load flow calculation and safety check comprises the steps of carrying out data aggregation, intelligent classification and real-time identification on data of the data acquisition and monitoring control system based on data acquisition and state identification, and judging whether the scheduling scheme meets the safety check requirement of the power system or not according to a load flow calculation result and the load flow requirement of the power distribution network by combining a load flow calculation strategy of the power system of the computer.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation system of the present invention, wherein: the voice recognition module comprises: used for confirming the identity of the dispatcher and storing the dispatching instruction; the face recognition module is connected with the voice recognition module and used for confirming face information of a dispatcher, comparing the face information with the voice recognition module and confirming the identity of the dispatcher secondarily; the knowledge base module is connected with the face recognition module: the system is used for storing a scheduling scheme and providing the scheduling scheme to the dispatcher who completes the secondary identity confirmation; the rule base module is connected with the knowledge base module and is used for storing the scheduling rules and judging the scheduling rules of the scheduling scheme; and the load flow calculation and safety check module is connected with the rule base module and is used for carrying out load flow calculation and safety check on the electric power system implementing the scheduling scheme and judging the feasibility of the scheduling scheme.
As a preferred scheme of the artificial intelligence-based power scheduling intelligent agent implementation system of the present invention, wherein: the scheduling rules comprise main transformer operation rules, bus operation rules, line operation rules, switch operation rules and operation rules of secondary equipment.
The invention has the beneficial effects that: the invention can confirm the information of the dispatching personnel by the voice recognition and image recognition technology, thereby further improving the safety of the dispatching process; meanwhile, an artificial intelligence technology is applied to the dispatching work of the power system, the existing dispatching method is optimized, and the intelligent dispatching of the power system is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart illustrating a method for implementing an intelligent agent for power scheduling based on artificial intelligence according to a first embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a voice recognition process of a power scheduling intelligent agent implementation method based on artificial intelligence according to a first embodiment of the present invention;
fig. 3 is a schematic diagram illustrating an image recognition process of an artificial intelligence-based power scheduling intelligent agent implementation method according to a first embodiment of the present invention;
fig. 4 is a schematic block diagram illustrating a distribution of an artificial intelligence based power scheduling intelligent agent implementation system according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 3, a first embodiment of the present invention provides an artificial intelligence-based power scheduling intelligent agent implementation method, including:
s1: after the voice recognition module 100 receives the dispatching command of the upper dispatcher, the identity of the upper dispatcher is confirmed through the voice recognition module 100 and the face recognition module 200.
It should be noted that the speech recognition module 100 is a speech recognition chip, such as an NRK10 speech recognition chip and an LD3320A speech recognition chip, in which a speech recognition algorithm (e.g., a hidden markov model algorithm based on a dynamic time warping algorithm and a parameter model) is embedded, and referring to fig. 2, the speech recognition chip is used to collect speech information and recognition scheduling instructions of a superior dispatcher, and then the speech recognition algorithm is used to match the speech information of the superior dispatcher according to the speech information and a constructed speech library, and output identity information of the dispatcher in an information library; referring to fig. 3, the facial recognition module 200 performs facial information of the dispatcher by using the collecting camera, acquires facial features of the dispatcher by combining with a facial recognition algorithm (e.g., a template matching algorithm, a local preserving projection algorithm), and finally performs information matching of the dispatcher in the constructed image library by using the facial recognition algorithm.
The voice database is used for carrying out voice data mining on the recording data in the process of overhauling the past year by utilizing a convolutional neural network to obtain the voice characteristics of the power grid dispatching personnel; the image library is the facial features of the power grid dispatching personnel obtained by learning the image information of the power grid dispatching personnel by using the convolutional neural network.
The identity of a superior dispatcher is confirmed through the voice recognition module 100 and the face recognition module 200, and if the identity of the superior dispatcher is correct, the operation data of the power system and the dispatching scheme of the knowledge base module 300 are acquired; otherwise, the identity of the superior dispatcher is confirmed again; wherein the operating data of the power system comprises: node current, voltage and power.
S2: and performing load flow calculation and safety check through the load flow calculation and safety check module 400 according to the operation data, and judging whether the scheduling scheme of the knowledge base module 300 meets the safety check requirement of the power system.
It should be noted that the knowledge base module 300 is a knowledge base of scheduling schemes, and the scheduling schemes in the scheduling scheme base are derived from: (1) scheduling experience of scheduling experts and existing scheduling schemes; (2) the method is based on the existing scheduling scheme and expert experience, and combines the learning and optimization of an artificial intelligence algorithm, so as to achieve the aim of meeting the requirements of fewer steps of load flow calculation, safety check and operation ticket opening and closing, and finally form a set of power grid scheduling scheme.
The power flow calculation and security check module 400 is used for calculating the judgment of the power flow calculation and scheduling scheme of the power system, and specifically, performs data aggregation on data of the data acquisition and monitoring control system based on data acquisition and state identification (which means that the data are divided into aggregation classes according to the intrinsic properties of the data, elements in each aggregation class have the same characteristics as much as possible, and characteristic differences among different aggregation classes are as large as possible), intelligent classification (information after clustering is divided into several classes based on artificial intelligence and is just like the sense of chapter catalogue, so that the efficiency is increased), real-time identification (real-time identification of collected power grid operation data), and combines with a computer power system power flow calculation strategy to judge whether the scheduling scheme meets the security check requirement of the power system (based on the collected power system operation data, comparing the dynamic thermal stability with the rated value).
If the scheduling scheme of the knowledge base module 300 meets the requirements, sending a scheduling instruction to a next-level dispatcher; otherwise, the scheduling scheme is acquired again.
S3: the voice identity information of the subordinate dispatcher and the dispatching instruction voice information are confirmed through the voice recognition module 100.
If the identity of the subordinate dispatcher is correct, judging the rule of the dispatching instruction; otherwise, performing abnormal dispatcher identity feedback on the condition of the inconsistent dispatcher identity;
if the rule is not in accordance with the scheduling instruction, feedback is carried out when the rule is not in accordance with the scheduling rule; otherwise, the lower-level dispatcher repeats the dispatching instruction to the upper-level dispatcher.
When the lower-level dispatcher repeats the dispatching instruction, waiting for the confirmation of the upper-level dispatcher; if the upper-level dispatcher confirms that the dispatching instruction is correct, the lower-level dispatcher executes the given dispatching instruction; and if the upper-level dispatcher does not confirm the dispatching instruction, feeding back the unconfirmed dispatching instruction to the upper-level dispatcher.
In order to verify and explain the technical effects adopted in the method, the embodiment selects the traditional data enhancement method and adopts the method to perform comparison test, and compares the test results by means of scientific demonstration to verify the real effect of the method.
In order to verify that the method has higher robustness compared with the traditional data enhancement method, the traditional data enhancement method and the method are adopted to carry out optimization measurement comparison on the convolutional neural network respectively.
The input data of the model is that the input of the network is a 4-dimensional tensor with the size of (128, 32, 32, 3), which respectively represents the number of a batch of pictures 128, the number of wide pixels of the pictures 32, the number of high pixels 32 and the number of channels 3;
firstly, extracting the characteristics of an image by using a plurality of convolutional neural network layers, wherein the calculation process of the convolutional neural network layers comprises the following steps:
the convolutional layer 1: convolution kernel size 3 x 3, convolution kernel move step 1, convolution kernel number 64, pooling size 2 x 2, pooling step 2, pooling type maximum pooling, activation function ReLU.
And (3) convolutional layer 2: convolution kernel size 3 x 3, convolution kernel move step 1, convolution kernel number 128, pooling size 2 x 2, pooling step 2, pooling type maximum pooling, activation function ReLU.
And (3) convolutional layer: convolution kernel size 3 × 3, convolution kernel move step 1, convolution kernel number 256, pooling size 2 × 2, pooling step 2, pooling type being maximum pooling, activation function ReLU.
Full connection layer: number of hidden layer units 1024, activation function ReLU.
A classification layer: number of hidden layer elements 10, activation function softmax.
Parameters were initialized, random _ normal (0.0, 0.001) was used for all weight matrices, constant (0.0) was used for all bias vectors, crosssense was used as an objective function, parameter update was performed by Adam gradient descent method, and the learning rate was set to a fixed value of 0.001.
In order to carry out a comparison experiment, the performance of the traditional data enhancement method and the method is observed, the two methods are trained for 5000 rounds, and the loss change condition and the training set accuracy change condition are observed as shown in the following table.
Table 1: and optimizing a convolutional neural network training result comparison table.
The table shows that the method not only can make the loss of the training process more stable, but also can improve the accuracy of the test set to about 90%, and the optimization effect is obviously superior to that of the traditional data enhancement method.
Example 2
Referring to fig. 4, a second embodiment of the present invention is different from the first embodiment in that an artificial intelligence based power scheduling intelligent agent implementation system is provided, including:
the speech recognition module 100: used for confirming the identity of the dispatcher and storing the dispatching instruction; specifically, the voice recognition module 100 is an LD3320 voice recognition chip, the voice recognition module 100 first collects voice information of a dispatcher, performs dispatch personnel information matching in a voice library (voice characteristics of a power grid dispatcher obtained by performing voice data mining on recording data in a maintenance process of a past year by using a convolutional neural network) by combining an embedded voice recognition algorithm according to the collected voice information of the dispatcher, and outputs identity information of the dispatcher in the information library.
The face recognition module 200 is connected with the voice recognition module 100 and is used for confirming face information of the dispatcher, comparing the face information with the face information of the voice recognition module 100 and confirming the identity of the dispatcher secondarily; specifically, the facial recognition module 100 collects information of the dispatching personnel by using a camera, acquires facial pictures of the dispatching personnel by combining a facial recognition algorithm, and finally performs information matching of the dispatching personnel in an image library (facial features of the dispatching personnel of the power grid obtained by learning image information of the dispatching personnel of the power grid by using a convolutional neural network) by using the facial recognition algorithm.
The knowledge base module 300 is connected with the face recognition module 200: the system is used for storing the scheduling scheme and providing the scheduling scheme for a dispatcher who completes secondary identity confirmation; specifically, the knowledge base module 300 may be an sql (structured Query language) database, and the scheduling scheme is derived from: (1) scheduling experience of scheduling experts and existing scheduling schemes; (2) the method is characterized in that the existing scheduling scheme and expert experience are combined with learning and optimization of an artificial intelligence algorithm, the steps required by load flow calculation, safety check and operation ticket opening and closing are less, and finally a set of power grid scheduling scheme is formed.
The rule base module 400 is connected with the knowledge base module 300 and is used for storing the scheduling rules and judging the scheduling rules of the scheduling scheme; specifically, the scheduling rules give basic rules to be followed when the power system scheduling instruction is performed, such as the order and requirements of operations, to the rule base; the rule base determines the scheduling instructions generated by the intelligent power scheduling agent system and the sequence of each scheduling instruction, and has great significance for the scientificity and the accuracy of the scheduling of the power system, and the rule base comprises a main transformer operation rule, a bus operation rule, a line operation rule, a switch operation rule and an operation rule of secondary equipment.
The dispatching operation of the power system refers to that the electrical equipment is switched from one use state to another use state, and the states of the electrical equipment are divided into five types, namely operation, cold standby, hot standby, power failure and maintenance; some rules to be followed in power system scheduling operations are as follows:
(1) when power is transmitted, the power supply side is firstly connected with the load side, namely, the switching equipment on the power supply side is firstly connected with the switching equipment on the load side.
(2) When power is cut off, the load side is firstly pulled and then the power supply side is pulled, namely, the switch equipment on the load side is pulled firstly and then the switch equipment on the power supply side is pulled.
(3) Molding the breaker to be in the off position when operating the disconnector; the isolating switch is strictly prohibited to be pulled and closed under the load.
(4) When the circuit is in power failure, after the breaker is disconnected, the disconnecting switch on the circuit side is pulled first, the disconnecting switch on the bus side is pulled later, and the situation is just opposite to the situation when the circuit is in power transmission.
(5) When one transformer of a transformer substation needs to be overhauled, the state of bus tie switches at two sides of the transformer is needed; if the bus coupler switch is in an off state, the bus coupler switch needs to be closed firstly, so that the system is in a closed loop running state; and after the system is confirmed to be in the closed loop operation state, the operation of the transformer is changed to maintenance.
(6) When two groups of transformers run in parallel, the requirements of identical phase, identical wiring group, identical voltage ratio, no more than 10% of short-circuit voltage difference and no more than 3% of capacity ratio are met: 1.
the load flow calculation and safety check module 500 is connected with the rule base module 400, and is used for performing load flow calculation and safety check on the power system after the scheduling scheme is implemented, and judging the feasibility of the scheduling scheme; specifically, the load flow calculation and security check module 500 performs data aggregation, intelligent classification and real-time identification on the SCADA data based on data acquisition and state identification, and determines whether the scheduling scheme meets the security check requirement of the power system according to the load flow calculation result and the power distribution network load flow requirement by combining a load flow calculation method of the computer power system.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (8)
1. An artificial intelligence-based power dispatching intelligent agent implementation method is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
after a voice recognition module (100) receives a dispatching instruction of a superior dispatcher, the identity of the superior dispatcher is confirmed through the voice recognition module (100) and a face recognition module (200), and if the identity of the superior dispatcher is correct, operation data of the power system and a dispatching scheme of a knowledge base module (300) are acquired; otherwise, the identity of the superior dispatcher is confirmed again;
according to the operation data, load flow calculation and safety check are carried out through a load flow calculation and safety check module (400), and whether the scheduling scheme of the knowledge base module (300) meets the safety check requirement of the power system is judged;
if the requirement is met, sending a scheduling instruction to a lower-level dispatcher; otherwise, the scheduling scheme is obtained again;
confirming voice identity information and scheduling instruction voice information of the subordinate dispatcher through a voice recognition module (100); if the identity of the subordinate dispatcher is correct, judging the rule of the dispatching instruction; otherwise, performing dispatcher identity abnormity feedback;
if the rule is not in accordance with the scheduling instruction, feedback is carried out when the rule is not in accordance with the scheduling rule; otherwise, the lower-level dispatcher repeats the dispatching instruction to the upper-level dispatcher.
2. The artificial intelligence based power scheduling intelligent agent implementation method of claim 1, wherein: also comprises the following steps of (1) preparing,
if the superior dispatcher confirms that the dispatching instruction is correct, the subordinate dispatcher executes the dispatching instruction; and if the superior dispatcher does not confirm the dispatching instruction, feeding back the unconfirmed dispatching instruction to the superior dispatcher.
3. The artificial intelligence based power scheduling intelligent agent implementation method of claim 1, wherein: confirming the identity of the superior dispatcher includes,
the voice recognition module (100) collects voice information of a superior dispatcher and recognizes the dispatching instruction by using a voice recognition chip, and performs voice information matching on the superior dispatcher by combining a voice recognition algorithm according to the voice information and a built voice library;
the face recognition module (200) collects face information of a superior dispatcher by using a camera, and performs face information matching on the superior dispatcher in a constructed image library by using a face recognition algorithm.
4. The method of claim 3, wherein the method comprises: the constructed voice library and the image library include,
performing voice data mining on the recording data in the process of maintenance over the years by using a convolutional neural network to obtain voice characteristics of power grid dispatching personnel, namely the voice database;
the image library: and learning the image information of the power grid dispatching personnel by using a convolutional neural network to obtain the facial features of the power grid dispatching personnel, namely the image library.
5. The artificial intelligence based power scheduling intelligent agent implementation method according to claim 3 or 4, wherein: the scheduling scheme may include the steps of,
scheduling experience of scheduling experts and existing scheduling schemes.
6. The artificial intelligence based power scheduling intelligent agent implementation method of claim 5, wherein: the power flow calculation and the safety check comprise that,
and performing data aggregation, intelligent classification and real-time identification on data of the data acquisition and monitoring control system based on data acquisition and state identification, and judging whether the scheduling scheme meets the safety check requirement of the power system according to a load flow calculation result and the load flow requirement of the power distribution network by combining a load flow calculation strategy of the computer power system.
7. The utility model provides a power scheduling wisdom agent implementation system based on artificial intelligence which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
speech recognition module (100): used for confirming the identity of the dispatcher and storing the dispatching instruction;
the face recognition module (200) is connected with the voice recognition module (100) and is used for confirming face information of a dispatcher and secondarily confirming the identity of the dispatcher by comparing the voice recognition module (100);
the knowledge base module (300) is connected with the face recognition module (200): the system is used for storing a scheduling scheme and providing the scheduling scheme to the dispatcher who completes the secondary identity confirmation;
the rule base module (400) is connected with the knowledge base module (300) and is used for storing the scheduling rules and judging the scheduling rules of the scheduling scheme;
and the load flow calculation and safety check module (500) is connected with the rule base module (400) and is used for carrying out load flow calculation and safety check on the electric power system after the scheduling scheme is implemented and judging the feasibility of the scheduling scheme.
8. The artificial intelligence based power scheduling intelligent agent implementation system of claim 7, wherein: the scheduling rules may include, for example,
main transformer operating rules, bus operating rules, line operating rules, switch operating rules and secondary equipment operating rules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420336.3A CN113283695A (en) | 2021-04-19 | 2021-04-19 | Power dispatching intelligent agent implementation method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420336.3A CN113283695A (en) | 2021-04-19 | 2021-04-19 | Power dispatching intelligent agent implementation method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113283695A true CN113283695A (en) | 2021-08-20 |
Family
ID=77276882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110420336.3A Pending CN113283695A (en) | 2021-04-19 | 2021-04-19 | Power dispatching intelligent agent implementation method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283695A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763954A (en) * | 2021-09-10 | 2021-12-07 | 河南华东工控技术有限公司 | SCADA configuration interface operation method based on voice recognition technology |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109218433A (en) * | 2018-09-29 | 2019-01-15 | 广东电网有限责任公司 | A kind of distribution scheduling based on mobile terminal is issued an order system |
| CN110956357A (en) * | 2019-10-10 | 2020-04-03 | 国网浙江省电力有限公司宁波供电公司 | Intelligent regulation and control networked interaction system applied to power company |
| CN111462754A (en) * | 2020-04-16 | 2020-07-28 | 深圳航天科创实业有限公司 | Method for establishing dispatching control voice recognition model of power system |
| CN112000938A (en) * | 2020-07-15 | 2020-11-27 | 国网山东省电力公司信息通信公司 | Power grid dispatching identity authentication method and system based on multimode identification |
| CN112599124A (en) * | 2020-11-20 | 2021-04-02 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Voice scheduling method and system for power grid scheduling |
-
2021
- 2021-04-19 CN CN202110420336.3A patent/CN113283695A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109218433A (en) * | 2018-09-29 | 2019-01-15 | 广东电网有限责任公司 | A kind of distribution scheduling based on mobile terminal is issued an order system |
| CN110956357A (en) * | 2019-10-10 | 2020-04-03 | 国网浙江省电力有限公司宁波供电公司 | Intelligent regulation and control networked interaction system applied to power company |
| CN111462754A (en) * | 2020-04-16 | 2020-07-28 | 深圳航天科创实业有限公司 | Method for establishing dispatching control voice recognition model of power system |
| CN112000938A (en) * | 2020-07-15 | 2020-11-27 | 国网山东省电力公司信息通信公司 | Power grid dispatching identity authentication method and system based on multimode identification |
| CN112599124A (en) * | 2020-11-20 | 2021-04-02 | 内蒙古电力(集团)有限责任公司电力调度控制分公司 | Voice scheduling method and system for power grid scheduling |
Non-Patent Citations (2)
| Title |
|---|
| 周全仁等: "《现代电网自动控制系统及其应用》" * |
| 裴俊等: "基于人工智能的配网网络发令系统及应用", 《机械与电子》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763954A (en) * | 2021-09-10 | 2021-12-07 | 河南华东工控技术有限公司 | SCADA configuration interface operation method based on voice recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Karapidakis et al. | Online preventive dynamic security of isolated power systems using decision trees | |
| CN105098762B (en) | A kind of isolated island division methods containing distributed power distribution network | |
| CN107123989A (en) | A kind of topology identification method based on improved local outlier factor algorithm | |
| Zhao et al. | Distributed risk-limiting load restoration for wind power penetrated bulk system | |
| CN106355308A (en) | Method for identifying key equipment of wind power access system based on decision tree | |
| CN111652478B (en) | Umbrella algorithm-based power system voltage stability evaluation misclassification constraint method | |
| CN103440398B (en) | A kind of grid branch importance appraisal procedure based on pattern recognition | |
| CN113283695A (en) | Power dispatching intelligent agent implementation method and system based on artificial intelligence | |
| CN115693652A (en) | Power distribution network frame optimization method and device based on power balance and performance cost | |
| Huang et al. | An intelligent system for advanced dynamic security assessment | |
| CN108304976A (en) | A kind of electric system fining load prediction and analysis method | |
| CN105790256B (en) | Power distribution network access distributed generation unit critical path recognition methods based on multi-agent technology | |
| CN113344283B (en) | Energy internet new energy consumption capability assessment method based on edge intelligence | |
| CN114204675A (en) | Power distribution station electric energy data acquisition terminal based on cloud edge cooperation | |
| Skolthanarat et al. | Short-term load forecasting algorithm and optimization in smart grid operations and planning | |
| CN116956203A (en) | Method and system for measuring action characteristics of tapping switch of transformer | |
| Li et al. | A probabilistic data-driven method for response-based load shedding against fault-induced delayed voltage recovery in power systems | |
| CN107256415A (en) | A kind of computational methods and computing system of power system operation mode scene | |
| CN115549075A (en) | Power supply recovery method and system for power distribution network containing micro-grid | |
| CN103296678A (en) | Online assistant decision making method for large power grid restoration | |
| CN110751328A (en) | High-proportion renewable energy power grid adaptive planning method based on joint weighted entropy | |
| CN114648297A (en) | Mass power grid infrastructure project optimization method considering project association characteristics | |
| CN115496427A (en) | Flexible interconnection investment planning decision method for multi-microgrid system | |
| CN112270084B (en) | Data-driven high-proportion renewable energy power system operation scene identification method | |
| CN115118015A (en) | Platform district power supply stability monitoring system based on fuse terminal |
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 |