CN116258282B - Smart grid resource scheduling and distributing method based on cloud platform - Google Patents
Smart grid resource scheduling and distributing method based on cloud platform Download PDFInfo
- Publication number
- CN116258282B CN116258282B CN202310533532.0A CN202310533532A CN116258282B CN 116258282 B CN116258282 B CN 116258282B CN 202310533532 A CN202310533532 A CN 202310533532A CN 116258282 B CN116258282 B CN 116258282B
- Authority
- CN
- China
- Prior art keywords
- power
- data
- electric power
- power distribution
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000009826 distribution Methods 0.000 claims abstract description 358
- 238000012545 processing Methods 0.000 claims abstract description 215
- 229920000832 Cutin Polymers 0.000 claims abstract description 84
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000005520 cutting process Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 52
- 238000002347 injection Methods 0.000 claims description 36
- 239000007924 injection Substances 0.000 claims description 36
- 238000004458 analytical method Methods 0.000 claims description 32
- 239000013598 vector Substances 0.000 claims description 32
- 238000003066 decision tree Methods 0.000 claims description 29
- 238000007477 logistic regression Methods 0.000 claims description 28
- 238000004140 cleaning Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 230000002776 aggregation Effects 0.000 claims description 10
- 238000004220 aggregation Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000005094 computer simulation Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012384 transportation and delivery Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 17
- 238000004364 calculation method Methods 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 13
- 230000002159 abnormal effect Effects 0.000 description 8
- 230000003993 interaction Effects 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 7
- 238000013439 planning Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013468 resource allocation Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/72—Data preparation, e.g. statistical preprocessing of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Power Engineering (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Geometry (AREA)
- Educational Administration (AREA)
- Biodiversity & Conservation Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of intelligent power grid resource scheduling, in particular to a cloud platform-based intelligent power grid resource scheduling and distributing method. The steps include the steps of: acquiring intelligent power grid data of a cloud platform, importing the intelligent power grid data into a pre-constructed initial regional power distribution model for model training processing, generating a regional power distribution model, mapping the regional power distribution model, and generating a power distribution characteristic texture map; performing image superposition registration processing on the electric power distribution characteristic texture map to generate an electric power superposition image, and performing image cutting processing on the electric power superposition image to obtain an electric power superposition image block; performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data; and carrying out data preprocessing on the electric power image cutin data to generate standard electric power cutin data. The intelligent power grid resource scheduling and distributing method is realized by identifying and processing the intelligent power grid resource images.
Description
Technical Field
The invention relates to the technical field of intelligent power grid resource scheduling, in particular to a cloud platform-based intelligent power grid resource scheduling and distributing method.
Background
With the development of energy industry, smart grid technology is rapidly popularized and applied to establish a more efficient, intelligent and sustainable power production, transmission, distribution and use system. Resource allocation is a critical part of smart grid, and refers to a method for efficiently planning and configuring power resources in power system management to maintain stability and efficiency of power system operation. Resource allocation decisions are a complex optimization process that requires a comprehensive consideration of a variety of factors including, but not limited to, power supply and demand, grid structure, power price, energy type, environmental impact, etc. However, in the traditional power system, resource allocation is often limited by a fixed power supply mode, a geographic position and a scheduling rule, and the problem that the flow direction of regional power and the error of regional power flow direction are large cannot be accurately identified due to the lack of response capability to real-time change of power system operation, application requirements and the like, and meanwhile, when the regional voltage is overlarge, manual solution can only be passively performed.
Disclosure of Invention
Based on the above, the invention provides a smart grid resource scheduling and distributing method based on a cloud platform to solve at least one of the above technical problems.
In order to achieve the above purpose, a smart grid resource scheduling and distributing method based on a cloud platform comprises the following steps:
step S1: acquiring intelligent power grid data of a cloud platform, importing the intelligent power grid data into a pre-constructed initial regional power distribution model for model training processing, generating a regional power distribution model, mapping the regional power distribution model, and generating a power distribution characteristic texture map;
step S2: carrying out image superposition registration processing on the electric power distribution characteristic texture map by using a mirror symmetrical registration algorithm to generate an electric power superposition image; performing image cutting processing on the electric power superposition image to obtain an electric power superposition image block;
step S3: performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data; carrying out data preprocessing on the electric power image cutin data to generate standard electric power cutin data;
step S4: performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data; carrying out electric power data logistic regression processing on the electric power characteristic sensitive data by utilizing a logistic regression algorithm to obtain electric power regression data;
step S5: carrying out power decision training on the power regression data through a decision tree model to generate a power prediction model;
Step S6: carrying out optimal power behavior prediction on the power distribution data through a power prediction model so as to obtain optimal power distribution path data;
step S7: and carrying out dynamic simulation power injection processing on the optimal power distribution path data to generate an optimal power distribution path.
According to the method, the intelligent power grid data in the cloud platform are acquired, the intelligent power grid data are imported into the pre-built initial regional power distribution model for model training, the regional power distribution model is generated, the efficiency and reliability of power distribution are improved, the regional power distribution model is subjected to mapping processing, and the power distribution characteristic texture map is generated, so that the power distribution situation can be more intuitively known, power planning and management can be better performed, and the efficiency and reliability of power distribution are improved; the mirror symmetrical registration algorithm is utilized to carry out image registration processing on the electric power distribution characteristic texture map to generate an electric power registration image, so that the superposition precision and quality of the electric power distribution characteristic texture map can be effectively improved, the problems of rotation, translation, distortion and the like of the electric power distribution characteristic texture map are solved, higher matching flexibility and reliability are obtained, the electric power registration image is subjected to image cutting processing to obtain an electric power registration image block, the processing speed of a computer is improved, and the occupied space of a memory is reduced; the method comprises the steps of performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data, improving the definition and quality of an electric power image, reducing the probability of error judgment, performing data analysis and obtaining target information more quickly and accurately, performing data preprocessing on the electric power image cutin data to generate standard electric power cutin data, improving the accuracy and reliability of the electric power cutin data, reducing data analysis errors, and improving the application efficiency and effect of the electric power data; performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data, improving the efficiency of data processing and analysis, and performing electric power data logistic regression processing on the electric power feature sensitive data by using a logistic regression algorithm to obtain electric power regression data, improving the efficiency of subsequent processing and reducing the influence of uncertain factors; the power regression data is subjected to power decision training through the decision tree model, so that the accuracy and efficiency of power judgment can be improved, and the data can be processed later; the power distribution data is subjected to optimal power behavior prediction through a power prediction model so as to obtain optimal power distribution path data, a comprehensive and reasonable power dispatching plan is formulated, the operation efficiency of a power system is optimized, the utilization rate and stability of power are improved, and the energy consumption cost of society is reduced; and carrying out dynamic simulation power injection processing on the data of the optimal power distribution path to generate the optimal power distribution path, thereby improving the safety of the power system, reducing the power loss, improving the resource utilization rate and improving the economic benefit. Therefore, the intelligent power grid resource scheduling and distributing method of the cloud platform can microscopically and carefully analyze the power flow direction of the area, and autonomously schedule and distribute resources under different power conditions through the power prediction model, so that the problems of complicated manual steps and power measurement precision loss are saved.
Preferably, step S1 comprises the steps of:
s11, acquiring intelligent power grid data of a cloud platform, and identifying and processing the intelligent power grid data in a pre-constructed regional power distribution model to acquire two-dimensional grid elements;
step S12: performing three-dimensional discretization on the two-dimensional grid elements so as to generate three-dimensional view discrete points;
step S13: performing view aggregation treatment on the three-dimensional view discrete points to obtain a three-dimensional view aggregation image;
step S14: carrying out intelligent power grid historical data training processing on the three-dimensional view aggregated image to generate a regional power distribution model;
step S15: and performing laser point cloud projection processing on the regional power distribution model by using the homogeneous coordinate system so as to generate a power distribution characteristic texture map.
According to the intelligent power grid data management method, the intelligent power grid data of the cloud platform are acquired, and are identified and processed in the pre-built regional power distribution model, so that the state and the running condition of the power grid can be monitored and managed in real time, and the energy utilization rate is optimized; the three-dimensional discretization processing is carried out on the two-dimensional grid elements, so that the feature space can be expanded, the subsequent feature extraction processing is facilitated, the robustness of local information is enhanced, and the accuracy and stability of the subsequent data processing are improved; performing view aggregation treatment on the three-dimensional view discrete points, improving the accuracy of the model and improving the rendering effect of the model; the three-dimensional view aggregated image is subjected to intelligent power grid historical data training processing, so that power grid operation data can be better identified, and subsequent processing and identification are facilitated; and the homogeneous coordinate system is utilized to carry out laser point cloud projection processing on the regional power distribution model, so that the accuracy of power distribution identification can be improved.
Preferably, step S2 comprises the steps of:
step S21: mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and an electric power distribution mirror image view is generated;
step S22: generating an electric power distribution superposition view by superposition contrast processing of the electric power distribution mirror image view and the electric power distribution characteristic texture map;
step S23: performing binarization processing on the electric power distribution superposition view to generate an electric power distribution superposition binary image;
step S24: carrying out image data noise reduction processing on the electric power distribution superposition view to obtain a noise reduction electric power distribution diagram;
step S25: and carrying out power distribution image cutting processing on the power distribution enhancement map to generate a power superposition image block.
According to the invention, mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and some structures or areas deviating from central symmetry in the electric power distribution characteristic texture map are corrected, so that the attractiveness and the readability of the electric power distribution characteristic texture map are improved, and meanwhile, the comparison and the analysis of the electric power distribution characteristic texture map images are convenient; the electric power distribution mirror image view and the electric power distribution characteristic texture image are subjected to superposition contrast processing, so that the accuracy of electric power distribution characteristic identification is improved, and the visualization of the electric power distribution view is enhanced; the electric power distribution superposition view is subjected to binarization processing to generate an electric power distribution superposition binary image, so that the processing speed of a computer image can be improved, and the image noise interference is reduced; image data noise reduction processing is carried out on the electric power distribution superposition view, so that the readability and the accuracy of the image are improved, and the image misjudgment rate is reduced; and (3) carrying out electric power distribution image cutting processing on the electric power distribution enhancement map, and cutting the image into electric power superposition image blocks with the same size and type, so that the definition of the electric power superposition image can be improved, and the subsequent calculated amount is reduced.
Preferably, step S3 comprises the steps of:
step S31: performing edge line crack detection screening treatment by using a preset crack and crack value and an electric superposition image block, and removing the electric superposition image block smaller than the crack and crack value so as to generate a standard electric superposition image;
step S32: performing corner detection on the standard electric power superposition image by using a corner detection algorithm to generate an electric power superposition binary feature vector;
step S33: carrying out Hamming distance matching processing on the electric power superposition binary feature vector to generate electric power image cutin data;
step S34: carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; carrying out data cleaning on the filtered power image cutin data to generate cleaning and filtering image data; and carrying out gray value processing on the cleaning and filtering image data to obtain standard electric power cutin data.
According to the invention, the edge line crack detection screening treatment is carried out by utilizing the preset crack and gap value and the electric coincident image block, the electric coincident image block smaller than the crack and gap value is removed, so that a standard electric coincident image is generated, the electric coincident image meeting the standard can be screened out, the accuracy and the reliability of the electric coincident image are improved, the electric coincident image not meeting the standard is removed, and the workload and the time cost of subsequent treatment can be reduced; the corner detection algorithm is utilized to carry out cutin detection on the standard electric power superposition image, cutin values of the standard electric power superposition image are calculated, accuracy of electric power flow direction data is improved, and redundant calculation amount caused by traditional calculation of electric power flow direction line curvature is reduced; carrying out Hamming distance matching processing on the electric power superposition binary feature vectors, and carrying out matching and comparison on different electric power images so as to obtain the similarity or the difference between the electric power superposition binary feature vectors, and removing interference signals to improve the quality and the precision of data; carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; and (3) cleaning the filtered power image cutin data to remove repeated, wrong or incomplete data, improving the quality of the data and the subsequent analysis processing speed, performing gray value processing on the cleaned and filtered image data, converting the image into a black-white gray image, reducing the data amount of the image, and enhancing the image characteristics, thereby obtaining the standard power cutin data.
Preferably, step S4 comprises the steps of:
step S41: carrying out principal component analysis processing on standard electric power cutin data to obtain electric power distribution characteristic data;
step S42: vector decomposition processing is carried out on the power distribution characteristic data to generate a power distribution characteristic vector;
step S43: carrying out space construction processing on the power distribution feature vector by utilizing a covariance matrix algorithm to generate a power distribution feature space;
step S44: and carrying out space mapping processing on the power grid resource data in the power distribution characteristic space to obtain power characteristic sensitive data.
Step S45: and carrying out logistic regression processing on the power characteristic sensitive data according to a logistic regression algorithm to generate power regression data.
According to the invention, the standard electric power cutin data is subjected to principal component analysis treatment, so that a large amount of cutin data is converted into a few principal components, the cutin data structure is simplified, and the accuracy and reliability of data analysis are improved; vector decomposition processing is carried out on the power distribution characteristic data, and the power distribution characteristic data is decomposed into a plurality of subspaces, so that the reliability and the precision of the data are improved; carrying out space construction processing on the power distribution feature vector by utilizing a covariance matrix algorithm to generate a power distribution feature space, thereby better describing the features and rules of power distribution and carrying out monitoring and control on a power system; carrying out space mapping processing on the power grid resource data in the power distribution characteristic space, and converting the power grid resource data into distances and angles in the space, so as to obtain power characteristic sensitive data, and better carrying out subsequent power planning and management; and carrying out logistic regression processing on the power characteristic sensitive data according to a logistic regression algorithm to generate power regression data, so that the efficiency and accuracy of data processing are improved, and the workload and time cost of subsequent processing can be reduced.
Preferably, step S5 comprises the steps of:
step S51: performing data comparison processing on the electric power regression data and a preset electric power threshold, marking the electric power regression data as high-risk grade electric power data when the electric power regression data is larger than the electric power threshold, and marking the electric power regression data as common grade electric power data when the electric power regression data is smaller than the electric power threshold;
step S52: carrying out decision training processing on the high-risk level power data by utilizing a decision tree model, generating an emergency power signal when the power regression data is the high-risk level power data, and generating a normal power signal when the power regression data is the common level power data;
step S53: when the decision tree model acquires an emergency power signal, a high-risk power scheme is generated, and when the decision tree model acquires a normal power signal, a common power scheme is generated;
step S54: and carrying out power prediction training on the high-risk power prediction scheme and the common power prediction scheme to generate a power prediction model.
According to the invention, the electric power regression data and the preset electric power threshold value are subjected to data comparison processing, so that the electric power data can be effectively classified and rated, when the electric power regression data is larger than the electric power threshold value, the electric power regression data is marked as high-risk grade electric power data, the high-risk grade electric power data usually needs additional attention and control so as to ensure the stability and reliability of a system, and when the electric power regression data is smaller than the electric power threshold value, the electric power regression data is marked as common grade electric power data, and the common grade electric power data can provide various effective information and support; the decision tree model is utilized to carry out decision training processing on the high-risk level power data, when the power regression data is the high-risk level power data, an emergency power signal is generated, when the power regression data is the common level power data, a normal power signal is generated, and the signal can be perceived by the decision tree more easily, so that different decisions are used for different signals, the safety and the high efficiency of power distribution are improved, and the subsequent processing is convenient; when the decision tree model acquires an emergency power signal, a high-risk power scheme is generated, and when the decision tree model acquires a normal power signal, a common power scheme is generated, so that corresponding measures are taken to ensure normal operation of the power system, the normal operation of the power system is maintained, and meanwhile, the downtime and the cost are reduced to the greatest extent; by carrying out power prediction training on the high-risk power prediction scheme and the common power prediction scheme, the prediction precision is improved, the prediction is more robust, the problems of data deficiency, model overfitting and the like are solved, and a power prediction model is generated.
Preferably, step S6 comprises the steps of:
step S61: acquiring power distribution data, and performing historical data collection on the power distribution data to generate historical power distribution data;
step S62: according to the power prediction model, carrying out power path analysis processing on the historical power distribution data through a power distribution path formula to generate a power distribution path;
step S63: and carrying out path optimal analysis on the power distribution path by using an optimal power dispatching analysis formula to obtain optimal power distribution path data.
According to the invention, by acquiring the power distribution data and collecting the historical data of the power distribution data, the potential power trend and periodic change can be identified, the efficiency of subsequent power distribution is improved, and errors caused by repeated problems are avoided; according to the power prediction model, historical power distribution data is subjected to power path analysis processing through a power distribution path formula, so that balance between power supply and demand can be ensured, a beneficial power distribution path is generated, reasonable planning of power output and adjustment of a power distribution scheme are facilitated, power transmission loss is effectively controlled, and energy utilization efficiency is improved; and carrying out path optimal analysis on the power distribution path by utilizing an optimal power dispatching analysis formula to obtain optimal power distribution path data, so that the operation efficiency and economy of the power system can be effectively improved, and the cost and energy consumption are reduced.
Preferably, the power distribution path formula in step S62 is as follows:
in (1) the->Expressed as node +.>Power distribution path at->Expressed as node +.>Voltage at>Expressed as the total impedance of the power system, +.>Denoted as +.>Short-circuit capacity on a line, +.>Denoted as +.>Phase angle on line, +.>Expressed as power loss on the power distribution path, < >>Expressed as the number of resistors between all nodes, +.>Expressed as the +.>Charge capacity of the track current, ">Expressed as the potential difference between all nodes, +.>Expressed as the energy value in the circuit, +.>Represented as the power pressure value in the circuit distribution path, < >>Represented as a circuit distribution anomaly adjustment value generated from a power pressure value in a circuit distribution path and an energy value in the circuit.
The invention provides a power distribution path formula which fully considers nodesVoltage at->Total impedance of the power system->First->Short-circuit capacity on a strip line>First->Phase angle>Power loss on the power distribution path +.>Number of resistors between all nodes->The first part of the circuit distribution path>Charge capacity of the track current- >Potential difference between all nodes->Energy value in the circuit +.>Power pressure value in circuit distribution path +.>Based on the electric pressure value in the circuit distribution path and the potential difference between all nodes and the interaction between functions to form a functional relationshipBy->Phase angle on strip line and the firstThe interaction relation of short circuit capacity on the lines is used for extracting features under the condition of ensuring accurate data, and extracting the +.>Charge capacity of track current and using energy value in circuit and first>The circuit for generating the charge capacity of the current allocates an abnormal adjustment value, reduces data redundancy under the condition of ensuring accurate data, saves calculation force, enables calculation to achieve rapid convergence, and allocates the abnormal adjustment value through a circuit generated according to the power pressure value in a circuit allocation path and the energy value in the circuit>Adjusting the circuit distribution, generating the circuit distribution path coordinates more accurately>The accuracy and reliability of the power distribution path are improved. Meanwhile, parameters such as energy values, abnormal circuit allocation adjustment values and the like in the circuit in the formula can be adjusted according to actual conditions, so that the method is suitable for different circuit allocation scenes, and the applicability and flexibility of the algorithm are improved.
Preferably, the optimal power schedule analysis formula in step S63 is as follows:in (1) the->Is an optimal power scheduling function,/->Denoted as +.>Maximum cost of the individual power distribution paths +.>Is indicated at->Maximum power delivery selected on the path, +.>Denoted as +.>Minimum cost of the individual power distribution paths, +.>Is indicated at->Minimum power delivery on the path, < >>Expressed as power supply weight->Expressed as total required capacity of power,/->Expressed as total power capacity provided, +.>Represented as Lagrangian multiplier for limiting the scheme +.>Deviation between the total transport capacity of all paths and the required capacity, < >>Represented as an optimal power function correction value.
The invention provides an optimal power dispatching analysis formula which fully considers the firstMaximum cost of the individual power distribution paths +.>In->Maximum power transmission amount selected on the route +.>First->Minimum cost of the individual power distribution paths +.>In->Minimum power transmission amount selected on the route +.>Power supply weight->Total power demand capacity->Total power capacity provided->Lagrangian multiplier->According to the interaction between the power supply weight and the total power demand capacity and the function, a functional relation is formed >By->Maximum power transmission amount selected on the route +.>The interaction relation of the minimum cost of each power distribution path ensures that the data is accurate, performs data dimension reduction, extracts the total power demand capacity, and generates an optimal power scheduling function by utilizing Lagrangian multipliers and the total power capacity>The data redundancy is reduced under the condition of ensuring the accuracy of the data, the calculation force is saved, the calculation is enabled to achieve rapid convergence, and the correction value is corrected by the optimal power function +.>And the optimal circuit allocation is adjusted, so that an optimal power scheduling function is generated more accurately, and the accuracy and reliability of optimal power scheduling are improved. Meanwhile, parameters such as Lagrangian multipliers, power supply weights, optimal power function correction values and the like in the circuits in the formula can be adjusted according to actual conditions, so that the method is suitable for different circuit scheduling scenes, and applicability and flexibility of the algorithm are improved.
Preferably, step S7 comprises the steps of:
step S71: carrying out electric load test processing on intelligent power grid data of the cloud platform so as to obtain the maximum load capacity of the power grid;
step S72: performing simulated power injection processing on a preset power path in the cloud platform by utilizing the optimal power distribution path data to obtain a simulated power injection path;
Step S73: and performing power comparison processing on the simulated power injection path and the maximum load of the power grid, removing the simulated power injection path larger than the maximum load of the power grid, and generating an optimal power distribution path.
According to the method, the intelligent power grid data of the cloud platform are subjected to power load test processing so as to obtain the maximum load capacity of the power grid, so that the accuracy of analysis on the result of the maximum load capacity of the power grid can be improved, and the maximum load capacity of the power grid which can be born in practical application is evaluated so as to prevent faults such as overload and short circuit; the optimal power distribution path data is utilized to perform simulated power injection processing on a preset power path in the cloud platform, so that a simulated power injection path is obtained, better adjustment of a power distribution strategy can be facilitated, the rated power of a transmission line and equipment is ensured not to be exceeded, and the power performance characteristics are improved; and carrying out power comparison processing on the simulated power injection path and the maximum load of the power grid, removing the simulated power injection path larger than the maximum load of the power grid, generating an optimal power distribution path, improving the speed of data storage and processing, removing the path exceeding the maximum load of the power grid, and reducing possible errors of actual power distribution scheduling.
The beneficial effects of the invention are that by acquiring the intelligent power grid data in the cloud platform, as the intelligent power grid data is too redundant, therefore, the required power resource data and the regional modeling information need to be extracted to perform model training processing in the initial regional power distribution model to obtain a three-dimensional regional power distribution model, the model can intuitively see the regional power condition, and in order to facilitate data processing, therefore, the three-dimensional mapping process is carried out on the electric power distribution characteristic texture map, the three-dimensional points are mapped onto the two-dimensional image, the readability and the definition of data are improved, the mirror symmetry registration algorithm is utilized to carry out mirror image overturning on the electric power distribution characteristic texture map to obtain an overturning characteristic texture map, the electric power distribution characteristic texture map and the overturning characteristic texture map are overlapped to obtain an electric power overlapped image with a closed characteristic, the result is more accurate, the electric power overlapped image is subjected to image cutting process, the calculation time and the calculation time are saved, the load pressure of a system is reduced, and then edge cutin detection process is carried out on an electric power overlapped image block, thereby more accurately searching the size characteristics of the power flow direction, saving a large amount of resources, preprocessing the horny data of the power image, reducing the influence caused by useless, redundant and abnormal data, then carrying out logistic regression processing to obtain regression curve data, training the power regression data by a decision tree to generate different schemes under different decisions, so as to cope with various subsequent situations possibly occurring in the power distribution process, improve the safety of power distribution, utilize a power prediction model to perform power prediction, find out the optimal power distribution path under different conditions, and improve the utilization rate and stability of power. Therefore, the intelligent power grid resource scheduling and distributing method of the cloud platform can microscopically and carefully analyze the power flow direction of the area, and autonomously schedule and distribute resources under different power conditions through the power prediction model, so that the problems of complicated manual steps and power measurement precision loss are saved.
Drawings
Fig. 1 is a schematic flow chart of steps of a smart grid resource scheduling and distributing method based on a cloud platform;
FIG. 2 is a detailed flowchart illustrating the implementation of step S1 in FIG. 1;
FIG. 3 is a detailed flowchart illustrating the implementation of step S2 in FIG. 1;
FIG. 4 is a flowchart illustrating the detailed implementation of step S3 in FIG. 1;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The embodiment of the application provides a smart grid resource scheduling and distributing method based on a cloud platform, wherein the grid resources include but are not limited to: grid resource data, and the like.
To achieve the above objective, please refer to fig. 1 to 4, a method for scheduling and allocating resources of a smart grid based on a cloud platform, the method includes the following steps:
step S1: acquiring intelligent power grid data of a cloud platform, importing the intelligent power grid data into a pre-constructed initial regional power distribution model for model training processing, generating a regional power distribution model, mapping the regional power distribution model, and generating a power distribution characteristic texture map;
Step S2: carrying out image superposition registration processing on the electric power distribution characteristic texture map by using a mirror symmetrical registration algorithm to generate an electric power superposition image; performing image cutting processing on the electric power superposition image to obtain an electric power superposition image block;
step S3: performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data; carrying out data preprocessing on the electric power image cutin data to generate standard electric power cutin data;
step S4: performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data; carrying out electric power data logistic regression processing on the electric power characteristic sensitive data by utilizing a logistic regression algorithm to obtain electric power regression data;
step S5: carrying out power decision training on the power regression data through a decision tree model to generate a power prediction model;
step S6: carrying out optimal power behavior prediction on the power distribution data through a power prediction model so as to obtain optimal power distribution path data;
step S7: and carrying out dynamic simulation power injection processing on the optimal power distribution path data to generate an optimal power distribution path.
According to the method, the intelligent power grid data in the cloud platform are acquired, the intelligent power grid data are imported into the pre-built initial regional power distribution model for model training, the regional power distribution model is generated, the efficiency and reliability of power distribution are improved, the regional power distribution model is subjected to mapping processing, and the power distribution characteristic texture map is generated, so that the power distribution situation can be more intuitively known, power planning and management can be better performed, and the efficiency and reliability of power distribution are improved; the mirror symmetrical registration algorithm is utilized to carry out image registration processing on the electric power distribution characteristic texture map to generate an electric power registration image, so that the superposition precision and quality of the electric power distribution characteristic texture map can be effectively improved, the problems of rotation, translation, distortion and the like of the electric power distribution characteristic texture map are solved, higher matching flexibility and reliability are obtained, the electric power registration image is subjected to image cutting processing to obtain an electric power registration image block, the processing speed of a computer is improved, and the occupied space of a memory is reduced; the method comprises the steps of performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data, improving the definition and quality of an electric power image, reducing the probability of error judgment, performing data analysis and obtaining target information more quickly and accurately, performing data preprocessing on the electric power image cutin data to generate standard electric power cutin data, improving the accuracy and reliability of the electric power cutin data, reducing data analysis errors, and improving the application efficiency and effect of the electric power data; performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data, improving the efficiency of data processing and analysis, and performing electric power data logistic regression processing on the electric power feature sensitive data by using a logistic regression algorithm to obtain electric power regression data, improving the efficiency of subsequent processing and reducing the influence of uncertain factors; the power regression data is subjected to power decision training through the decision tree model, so that the accuracy and efficiency of power judgment can be improved, and the data can be processed later; the power distribution data is subjected to optimal power behavior prediction through a power prediction model so as to obtain optimal power distribution path data, a comprehensive and reasonable power dispatching plan is formulated, the operation efficiency of a power system is optimized, the utilization rate and stability of power are improved, and the energy consumption cost of society is reduced; and carrying out dynamic simulation power injection processing on the data of the optimal power distribution path to generate the optimal power distribution path, thereby improving the safety of the power system, reducing the power loss, improving the resource utilization rate and improving the economic benefit. Therefore, the intelligent power grid resource scheduling and distributing method of the cloud platform can microscopically and carefully analyze the power flow direction of the area, and autonomously schedule and distribute resources under different power conditions through the power prediction model, so that the problems of complicated manual steps and power measurement precision loss are saved.
In the embodiment of the present invention, as described with reference to fig. 1, a flow chart of steps of a method for scheduling and allocating resources of a smart grid based on a cloud platform is provided, where in this example, the steps of the method for scheduling and allocating resources of a smart grid based on a cloud platform include:
step S1: acquiring intelligent power grid data of a cloud platform, importing the intelligent power grid data into a pre-constructed initial regional power distribution model for model training processing, generating a regional power distribution model, mapping the regional power distribution model, and generating a power distribution characteristic texture map;
in the embodiment of the invention, the steps of acquiring intelligent power grid data of a cloud platform and a pre-constructed initial regional power distribution model comprise the following steps: collecting historical electricity consumption data and regional division data, carrying out data cleaning, integration and induction on the collected historical electricity consumption data and regional division data, extracting electric quantity and date characteristics, selecting factor analysis and statistics models, constructing an initial regional power distribution model, importing intelligent power grid data into the initial regional power distribution model for unsupervised learning training to generate a regional power distribution model, and carrying out three-dimensional mapping processing on the regional power distribution model to generate a power distribution characteristic texture map.
Step S2: carrying out image superposition registration processing on the electric power distribution characteristic texture map by using a mirror symmetrical registration algorithm to generate an electric power superposition image; performing image cutting processing on the electric power superposition image to obtain an electric power superposition image block;
in the embodiment of the invention, the mirror symmetrical registration algorithm is utilized to carry out image line overlapping comparison on the electric power characteristic distribution texture map, an electric power overlapping image is generated, and the electric power overlapping image is subjected to graph cutting with consistent size and type so as to obtain a plurality of electric power overlapping image blocks.
Step S3: performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data; carrying out data preprocessing on the electric power image cutin data to generate standard electric power cutin data;
in the embodiment of the invention, edge cutin detection is carried out on the electric power superposition image block, the protrusion degree of the edge cutin is detected, and electric power cutin data is obtained; the method comprises the steps of preprocessing electric power cutin data, wherein the preprocessing comprises data filtering, data cleaning, image gray value processing and comparison with a preset image edge crack value to generate standard electric power cutin data.
Step S4: performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data; carrying out electric power data logistic regression processing on the electric power characteristic sensitive data by utilizing a logistic regression algorithm to obtain electric power regression data;
In the embodiment of the invention, the standard electric power cutin data is subjected to vector decomposition by using a principal component analysis method, so that electric power characteristic data is extracted, electric power characteristic sensitive data is generated, and the electric power characteristic data is subjected to logistic regression processing by using a logistic regression algorithm to obtain electric power regression data.
Step S5: carrying out power decision training on the power regression data through a decision tree model to generate a power prediction model;
in the embodiment of the invention, the power regression data is compared according to different power thresholds to generate the high-risk level power data and the common level power data, and the high-risk level power data and the common level power data are classified through the decision tree model, so that the power prediction model is generated.
Step S6: carrying out optimal power behavior prediction on the power distribution data through a power prediction model so as to obtain optimal power distribution path data;
in the embodiment of the invention, the power distribution data is used for finding out the optimal power distribution path data of the high-risk prediction power scheme and the common power prediction scheme through a power distribution path formula and an optimal power scheduling analysis formula.
Step S7: and carrying out dynamic simulation power injection processing on the optimal power distribution path data to generate an optimal power distribution path.
In the embodiment of the invention, the optimal power distribution path data is acquired, and the optimal power distribution path data is imported into the cloud platform for dynamic simulation power injection, wherein the dynamic simulation power injection process comprises the following steps: setting an initial node voltage value and a generator power output value, and carrying out power injection by adjusting signals in a controller to obtain an optimal power distribution path.
Preferably, step S1 comprises the steps of:
s11, acquiring intelligent power grid data of a cloud platform, and identifying and processing the intelligent power grid data in a pre-constructed regional power distribution model to acquire two-dimensional grid elements;
step S12: performing three-dimensional discretization on the two-dimensional grid elements so as to generate three-dimensional view discrete points;
step S13: performing view aggregation treatment on the three-dimensional view discrete points to obtain a three-dimensional view aggregation image;
step S14: carrying out intelligent power grid historical data training processing on the three-dimensional view aggregated image to generate a regional power distribution model;
step S15: and performing laser point cloud projection processing on the regional power distribution model by using the homogeneous coordinate system so as to generate a power distribution characteristic texture map.
According to the intelligent power grid data management method, the intelligent power grid data of the cloud platform are acquired, and are identified and processed in the pre-built regional power distribution model, so that the state and the running condition of the power grid can be monitored and managed in real time, and the energy utilization rate is optimized; the three-dimensional discretization processing is carried out on the two-dimensional grid elements, so that the feature space can be expanded, the subsequent feature extraction processing is facilitated, the robustness of local information is enhanced, and the accuracy and stability of the subsequent data processing are improved; performing view aggregation treatment on the three-dimensional view discrete points, improving the accuracy of the model and improving the rendering effect of the model; the three-dimensional view aggregated image is subjected to intelligent power grid historical data training processing, so that power grid operation data can be better identified, and subsequent processing and identification are facilitated; and the homogeneous coordinate system is utilized to carry out laser point cloud projection processing on the regional power distribution model, so that the accuracy of power distribution identification can be improved.
As an example of the present invention, referring to fig. 2, a detailed implementation step flow diagram of step S1 in fig. 2 is shown, where step S1 includes:
s11, acquiring intelligent power grid data of a cloud platform, and identifying and processing the intelligent power grid data in a pre-constructed regional power distribution model to acquire two-dimensional grid elements;
in the embodiment of the invention, intelligent grid data of a cloud platform are acquired, two-dimensional grid data identification is carried out on the intelligent grid data, and two-dimensional grid elements are obtained, wherein the two-dimensional grid elements refer to a grid structure formed by a plurality of line segments or patches parallel to coordinate axes in a two-dimensional space, the two-dimensional grid structure can be regarded as a grid formed by a plurality of small squares, each small square is called a unit or element, the elements are generally the same in size and are arranged along the horizontal direction and the vertical direction, and parameters such as material characteristics, loads and the like are defined on each element.
Step S12: performing three-dimensional discretization on the two-dimensional grid elements so as to generate three-dimensional view discrete points;
in the embodiment of the invention, three-dimensional discretization processing is performed on two-dimensional grid elements, and the three-dimensional discretization processing process comprises the following steps: the two-dimensional grid is extended upwards to form a three-dimensional grid containing multiple layers, the distance between two adjacent voxels is determined, each voxel is regarded as a cube or a cube, the side length of each voxel is set to be a certain value, the coordinates of the center point of each element are calculated and used as three-dimensional discrete points, and corresponding visual angle values are given to each three-dimensional discrete point, so that the three-dimensional visual angle discrete points are generated.
Step S13: performing view aggregation treatment on the three-dimensional view discrete points to obtain a three-dimensional view aggregation image;
in the embodiment of the invention, three-dimensional discrete point original images of a plurality of view angles are firstly obtained, wherein the three-dimensional discrete point original images comprise a front view angle three-dimensional discrete point original image, a rear view angle three-dimensional discrete point original image, a left view angle three-dimensional discrete point original image, a right view angle three-dimensional discrete point original image and the like, the three-dimensional discrete point original images are preprocessed, the preprocessing comprises denoising, brightness adjustment and contrast adjustment, a corresponding depth map is generated for each original image by using a space triangulation method and a parallax mapping algorithm method, the depth information of each pixel point in the image is represented, a reference depth map is obtained by weighting and fusing the depth maps, and the original images are synthesized according to the reference depth map. Specifically, each pixel is interpolated according to the depth information to obtain a color value at the depth, then all the color values are synthesized into a new image, post-processing is performed on the synthesized image, such as adding effects of shadows, textures and the like, and finally the synthesized three-dimensional view angle aggregate image is output.
Step S14: carrying out historical data training processing on the intelligent power grid through the three-dimensional view aggregated image to generate a regional power distribution model;
In the embodiment of the invention, the three-dimensional visual angle aggregate image is acquired, wherein the three-dimensional visual angle aggregate image comprises information of a power grid topology, a power transmission line, a transformer substation, a cable and the like, data cleaning is carried out on the three-dimensional visual angle aggregate image data, a three-dimensional entity model of an electric power system is established, the three-dimensional entity model comprises all elements of a power plant, the transformer substation, the power transmission line, a load node and the like in the region, the running state of the electric power network is simulated and analyzed according to actual power supply and demand conditions, historical power supply and demand data is analyzed by using machine learning and data mining technology, various factors influencing power grid running and power distribution are found and analyzed, and the intelligent power grid historical data is used for testing and verifying the power distribution model based on the data analysis and modeling in the previous steps, so that a final regional power distribution model is generated.
Step S15: and performing laser point cloud projection processing on the regional power distribution model by using the homogeneous coordinate system so as to generate a power distribution characteristic texture map.
In the embodiment of the invention, the power distribution point cloud data of the region is acquired, a three-dimensional homogeneous coordinate system is established, each point is represented by a quaternion, such as x, y and z, the position of the point in a three-dimensional space, w represents the weight information of the point, a laser scanner is utilized to carry out laser matrix scanning, each three-dimensional point is projected onto a plane, and a power distribution characteristic texture map is established according to the position and the weight information of the projected pixel point.
Preferably, step S2 comprises the steps of:
step S21: mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and an electric power distribution mirror image view is generated;
step S22: generating an electric power distribution superposition view by superposition contrast processing of the electric power distribution mirror image view and the electric power distribution characteristic texture map;
step S23: performing binarization processing on the electric power distribution superposition view to generate an electric power distribution superposition binary image;
step S24: carrying out image data noise reduction processing on the electric power distribution superposition view to obtain a noise reduction electric power distribution diagram;
step S25: and carrying out power distribution image cutting processing on the power distribution enhancement map to generate a power superposition image block.
According to the invention, mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and some structures or areas deviating from central symmetry in the electric power distribution characteristic texture map are corrected, so that the attractiveness and the readability of the electric power distribution characteristic texture map are improved, and meanwhile, the comparison and the analysis of the electric power distribution characteristic texture map images are convenient; the electric power distribution mirror image view and the electric power distribution characteristic texture image are subjected to superposition contrast processing, so that the accuracy of electric power distribution characteristic identification is improved, and the visualization of the electric power distribution view is enhanced; the electric power distribution superposition view is subjected to binarization processing to generate an electric power distribution superposition binary image, so that the processing speed of a computer image can be improved, and the image noise interference is reduced; image data noise reduction processing is carried out on the electric power distribution superposition view, so that the readability and the accuracy of the image are improved, and the image misjudgment rate is reduced; and (3) carrying out electric power distribution image cutting processing on the electric power distribution enhancement map, and cutting the image into electric power superposition image blocks with the same size and type, so that the definition of the electric power superposition image can be improved, and the subsequent calculated amount is reduced.
As an example of the present invention, referring to fig. 3, a detailed implementation step flow diagram of step S2 in fig. 1 is shown, where step S2 includes:
step S21: mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and an electric power distribution mirror image view is generated;
in the embodiment of the invention, mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and the operations of folding, overturning and the like are carried out on the picture to generate an electric power distribution mirror image view.
Step S22: generating an electric power distribution superposition view by superposition contrast processing of the electric power distribution mirror image view and the electric power distribution characteristic texture map;
in the embodiment of the invention, the electric power distribution mirror image view and the electric power distribution characteristic texture map are subjected to texture coverage overlapping by means of fixed size overlapping comparison, so that the electric power distribution view is generated.
Step S23: performing binarization processing on the electric power distribution superposition view to generate an electric power distribution superposition binary image;
in the embodiment of the invention, the binarization processing is carried out on the electric power distribution superposition view, and the binarization processing can use common threshold segmentation algorithms, such as an OTSU algorithm, a self-adaptive threshold algorithm and the like. And removing the rest colors in the view, and only keeping the black and white colors to generate a power distribution superposition binary image.
Step S24: carrying out image data noise reduction processing on the electric power distribution superposition view to obtain a noise reduction electric power distribution diagram;
in the embodiment of the invention, the data noise reduction processing is carried out on the electric power distribution superposition view, and the method comprises the following substeps:
selecting a picture needing noise reduction, and judging whether the size of the picture is in a reasonable range or not;
selecting to use wavelet transformation to reduce noise according to the image characteristics;
according to the wavelet transformation noise reduction mode, adjusting the noise reduction frequency;
and (3) carrying out noise reduction processing on the image, decomposing the image data into a plurality of frequency bands, removing high-frequency noise, reconstructing the signal, generating noise-reduced data, and obtaining a noise-reduced power distribution diagram.
Step S25: and carrying out power distribution image cutting processing on the power distribution enhancement map to generate a power superposition image block.
In the embodiment of the invention, the image cutting processing is carried out on the electric power distribution enhancement map, and the electric power superposition image block is generated by using cutting algorithms such as threshold segmentation, region growth, edge detection and the like.
Preferably, step S3 comprises the steps of:
step S31: performing edge line crack detection screening treatment by using a preset crack and crack value and an electric superposition image block, and removing the electric superposition image block smaller than the crack and crack value so as to generate a standard electric superposition image;
Step S32: performing corner detection on the standard electric power superposition image by using a corner detection algorithm to generate an electric power superposition binary feature vector;
step S33: carrying out Hamming distance matching processing on the electric power superposition binary feature vector to generate electric power image cutin data;
step S34: carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; carrying out data cleaning on the filtered power image cutin data to generate cleaning and filtering image data; and carrying out gray value processing on the cleaning and filtering image data to obtain standard electric power cutin data.
According to the invention, the edge line crack detection screening treatment is carried out by utilizing the preset crack and gap value and the electric coincident image block, the electric coincident image block smaller than the crack and gap value is removed, so that a standard electric coincident image is generated, the electric coincident image meeting the standard can be screened out, the accuracy and the reliability of the electric coincident image are improved, the electric coincident image not meeting the standard is removed, and the workload and the time cost of subsequent treatment can be reduced; the corner detection algorithm is utilized to carry out cutin detection on the standard electric power superposition image, cutin values of the standard electric power superposition image are calculated, accuracy of electric power flow direction data is improved, and redundant calculation amount caused by traditional calculation of electric power flow direction line curvature is reduced; carrying out Hamming distance matching processing on the electric power superposition binary feature vectors, and carrying out matching and comparison on different electric power images so as to obtain the similarity or the difference between the electric power superposition binary feature vectors, and removing interference signals to improve the quality and the precision of data; carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; and (3) cleaning the filtered power image cutin data to remove repeated, wrong or incomplete data, improving the quality of the data and the subsequent analysis processing speed, performing gray value processing on the cleaned and filtered image data, converting the image into a black-white gray image, reducing the data amount of the image, and enhancing the image characteristics, thereby obtaining the standard power cutin data.
As an example of the present invention, referring to fig. 4, a detailed implementation step flow diagram of step S3 in fig. 1 is shown, where step S3 includes:
step S31: performing edge line crack detection screening treatment by using a preset crack and crack value and an electric superposition image block, and removing the electric superposition image block smaller than the crack and crack value so as to generate a standard electric superposition image;
in the embodiment of the invention, edge line crack detection screening processing is performed on the electric coincident image blocks by using preset crack slit values, wherein the preset crack slit values refer to the edge line shadow thickness values of the image blocks, and the size of the crack slit values represents the electric power size when the electric power flow direction is distributed, so that the electric coincident image blocks smaller than the crack slit values are removed, and a standard electric coincident image is generated.
Step S32: performing corner detection on the standard electric power superposition image by using a corner detection algorithm to generate an electric power superposition binary feature vector;
in the embodiment of the invention, the corner detection algorithm is utilized to detect the edge corner of the standard electric power superposition image, and the obtained parameters are utilized to detect the corner of the image by detecting the corner characteristics of the edge corner of the image block, such as the number of the corners, the degree of the corners, the slope of the corners and the like, so as to obtain the coordinates of the corners, thereby generating the electric power superposition binary characteristic vector.
Step S33: carrying out Hamming distance matching processing on the electric power superposition binary feature vector to generate electric power image cutin data;
in the embodiment of the invention, the electric power coincidence binary feature vector is subjected to Hamming distance matching by reading the electric power coincidence binary feature vector, selecting a proper Hamming distance matching algorithm, such as Hamming distance matching based on a lookup table, hamming distance matching based on quick hash and the like, so as to obtain a matching result, such as a matching distance, a matching position and the like, and according to the matching result, the horny data of the electric power image, such as coordinates of corner points, the number of the corner points and the like, is generated, so as to generate horny data of the electric power image.
Step S34: carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; carrying out data cleaning on the filtered power image cutin data to generate cleaning and filtering image data; and carrying out gray value processing on the cleaning and filtering image data to obtain standard electric power cutin data.
In the embodiment of the invention, feasibility filtering processing is carried out on the electric power image cutin data, including judging whether the data type is floating point type and the like, generating filtered electric power image data, carrying out data cleaning on the filtered electric power image cutin data, eliminating repeated and missing data, generating cleaning filtered image data, carrying out gray value processing on the cleaning filtered image data, carrying out histogram equalization, and generating standard electric power cutin data.
Preferably, step S4 comprises the steps of:
step S41: carrying out principal component analysis processing on standard electric power cutin data to obtain electric power distribution characteristic data;
step S42: vector decomposition processing is carried out on the power distribution characteristic data to generate a power distribution characteristic vector;
step S43: carrying out space construction processing on the power distribution feature vector by utilizing a covariance matrix algorithm to generate a power distribution feature space;
step S44: and carrying out space mapping processing on the power grid resource data in the power distribution characteristic space to obtain power characteristic sensitive data.
Step S45: and carrying out logistic regression processing on the power characteristic sensitive data according to a logistic regression algorithm to generate power regression data.
According to the invention, the standard electric power cutin data is subjected to principal component analysis treatment, so that a large amount of cutin data is converted into a few principal components, the cutin data structure is simplified, and the accuracy and reliability of data analysis are improved; vector decomposition processing is carried out on the power distribution characteristic data, and the power distribution characteristic data is decomposed into a plurality of subspaces, so that the reliability and the precision of the data are improved; carrying out space construction processing on the power distribution feature vector by utilizing a covariance matrix algorithm to generate a power distribution feature space, thereby better describing the features and rules of power distribution and carrying out monitoring and control on a power system; carrying out space mapping processing on the power grid resource data in the power distribution characteristic space, and converting the power grid resource data into distances and angles in the space, so as to obtain power characteristic sensitive data, and better carrying out subsequent power planning and management; and carrying out logistic regression processing on the power characteristic sensitive data according to a logistic regression algorithm to generate power regression data, so that the efficiency and accuracy of data processing are improved, and the workload and time cost of subsequent processing can be reduced.
In the embodiment of the invention, the covariance matrix is calculated according to the standardized data by carrying out principal component analysis processing on the standard electric power cutin data. The covariance matrix describes the relationship between the variables in the data set, for example, in a power system, the covariance matrix may represent the relationship between power generation and consumption, and the eigenvalues and corresponding eigenvectors are calculated by solving the eigenvalues of the covariance matrix. The feature value reflects the interpretation degree of variance in the original data by the feature vector, the feature vector is the direction of converting the original data into a new space, the principal component is selected according to the size of the feature value, the first k feature vectors can be selected as the principal component due to the descending arrangement of the feature values, most of variance is reserved, the power grid resource data is subjected to space mapping projection in the power distribution feature space, the power feature sensitive data is obtained, the power feature sensitive data is subjected to logistic regression processing by using a logistic regression algorithm, and the power regression data is generated.
Preferably, step S5 comprises the steps of:
step S51: performing data comparison processing on the electric power regression data and a preset electric power threshold, marking the electric power regression data as high-risk grade electric power data when the electric power regression data is larger than the electric power threshold, and marking the electric power regression data as common grade electric power data when the electric power regression data is smaller than the electric power threshold;
Step S52: carrying out decision training processing on the high-risk level power data by utilizing a decision tree model, generating an emergency power signal when the power regression data is the high-risk level power data, and generating a normal power signal when the power regression data is the common level power data;
step S53: when the decision tree model acquires an emergency power signal, a high-risk power scheme is generated, and when the decision tree model acquires a normal power signal, a common power scheme is generated;
step S54: and carrying out power prediction training on the high-risk power prediction scheme and the common power prediction scheme to generate a power prediction model.
According to the invention, the electric power regression data and the preset electric power threshold value are subjected to data comparison processing, so that the electric power data can be effectively classified and rated, when the electric power regression data is larger than the electric power threshold value, the electric power regression data is marked as high-risk grade electric power data, the high-risk grade electric power data usually needs additional attention and control so as to ensure the stability and reliability of a system, and when the electric power regression data is smaller than the electric power threshold value, the electric power regression data is marked as common grade electric power data, and the common grade electric power data can provide various effective information and support; the decision tree model is utilized to carry out decision training processing on the high-risk level power data, when the power regression data is the high-risk level power data, an emergency power signal is generated, when the power regression data is the common level power data, a normal power signal is generated, and the signal can be perceived by the decision tree more easily, so that different decisions are used for different signals, the safety and the high efficiency of power distribution are improved, and the subsequent processing is convenient; when the decision tree model acquires an emergency power signal, a high-risk power scheme is generated, and when the decision tree model acquires a normal power signal, a common power scheme is generated, so that corresponding measures are taken to ensure normal operation of the power system, the normal operation of the power system is maintained, and meanwhile, the downtime and the cost are reduced to the greatest extent; by carrying out power prediction training on the high-risk power prediction scheme and the common power prediction scheme, the prediction precision is improved, the prediction is more robust, the problems of data deficiency, model overfitting and the like are solved, and a power prediction model is generated.
In the embodiment of the invention, the electric power regression data is subjected to data comparison processing with a preset electric power threshold, when the electric power regression data is larger than the electric power threshold, the electric power regression data is marked as high-risk grade electric power data, when the electric power regression data is smaller than the electric power threshold, the electric power regression data is marked as common grade electric power data, the decision tree model is used for carrying out decision training processing on the high-risk grade electric power data, when the electric power regression data is the high-risk grade electric power data, an emergency electric power signal is generated, when the electric power regression data is the common grade electric power data, a normal electric power signal is generated, when the decision tree model acquires the emergency electric power signal, a high-risk electric power scheme is generated, when the decision tree model acquires the normal electric power signal, the common electric power scheme is generated, and the electric power prediction training is carried out on the high-risk electric power prediction scheme and the common electric power prediction scheme, so that the electric power prediction model is generated.
Preferably, step S6 comprises the steps of:
step S61: acquiring power distribution data, and performing historical data collection on the power distribution data to generate historical power distribution data;
step S62: according to the power prediction model, carrying out power path analysis processing on the historical power distribution data through a power distribution path formula to generate a power distribution path;
Step S63: and carrying out path optimal analysis on the power distribution path by using an optimal power dispatching analysis formula to obtain optimal power distribution path data.
According to the invention, by acquiring the power distribution data and collecting the historical data of the power distribution data, the potential power trend and periodic change can be identified, the efficiency of subsequent power distribution is improved, and errors caused by repeated problems are avoided; according to the power prediction model, historical power distribution data is subjected to power path analysis processing through a power distribution path formula, so that balance between power supply and demand can be ensured, a beneficial power distribution path is generated, reasonable planning of power output and adjustment of a power distribution scheme are facilitated, power transmission loss is effectively controlled, and energy utilization efficiency is improved; and carrying out path optimal analysis on the power distribution path by utilizing an optimal power dispatching analysis formula to obtain optimal power distribution path data, so that the operation efficiency and economy of the power system can be effectively improved, and the cost and energy consumption are reduced.
In the embodiment of the invention, the type and the time range of the power distribution data to be collected are determined by acquiring the power distribution data, so that historical power distribution data is generated, the historical power distribution data is subjected to power path analysis processing through a power distribution path formula according to a power prediction model, a power distribution path is generated, and the power distribution path is subjected to path optimal analysis by utilizing an optimal power dispatching analysis formula to obtain optimal power distribution path data.
Preferably, the power distribution path formula in step S62 is as follows:
in (1) the->Expressed as node +.>Power distribution path at->Expressed as node +.>Voltage at>Expressed as the total impedance of the power system, +.>Denoted as +.>Short-circuit capacity on a line, +.>Denoted as +.>Phase angle on line, +.>Expressed as power loss on the power distribution path, < >>Expressed as the number of resistors between all nodes, +.>Represented as circuit distribution pathsGo up to->Charge capacity of the track current, ">Expressed as the potential difference between all nodes, +.>Expressed as the energy value in the circuit, +.>Represented as the power pressure value in the circuit distribution path, < >>Represented as a circuit distribution anomaly adjustment value generated from a power pressure value in a circuit distribution path and an energy value in the circuit.
The invention provides a power distribution path formula which fully considers nodesPower distribution path at->Node->Voltage at->Total impedance of the power system->First->Short-circuit capacity on a strip line>First->Phase angle>Power loss on the power distribution path +.>Number of resistors between all nodes->The first part of the circuit distribution path >Charge capacity of the track current->Potential difference between all nodes->Energy value in the circuit +.>Power pressure value in circuit distribution path +.>Circuit distribution abnormality adjustment value for generating power pressure value in circuit distribution path and energy value in circuit>Based on the electric pressure value in the circuit distribution path and the potential difference between all nodes and the interaction between functions to form a functional relationship
By->Phase angle on strip line +.>Short-circuit capacity phase on strip lineThe interaction relation, the feature extraction is carried out under the condition of ensuring the accuracy of the data, and the +.>Charge capacity of track current and using energy value in circuit and first>The charge capacity generating circuit of the track current distributes an abnormal adjustment value, reduces data redundancy under the condition of ensuring accurate data, saves calculation force, ensures that calculation achieves rapid convergence, and distributes the abnormal adjustment value through the circuit>The circuit distribution is adjusted, so that the circuit distribution path coordinates are generated more accurately, and the accuracy and reliability of the power distribution path are improved. Meanwhile, parameters such as energy values, abnormal circuit allocation adjustment values and the like in the circuit in the formula can be adjusted according to actual conditions, so that the method is suitable for different circuit allocation scenes, and the applicability and flexibility of the algorithm are improved.
Preferably, the optimal power schedule analysis formula in step S63 is as follows:
in (1) the->Is an optimal power scheduling function,/->Denoted as +.>Maximum cost of the individual power distribution paths +.>Is indicated at->Maximum power delivery selected on the path, +.>Denoted as +.>Minimum cost of the individual power distribution paths, +.>Is indicated at->Minimum power delivery on the path, < >>Expressed as power supply weight->Expressed as total required capacity of power,/->Expressed as total power capacity provided, +.>Represented as Lagrangian multiplier for limiting the scheme +.>Deviation between the total transport capacity of all paths and the required capacity, < >>Represented as an optimal power function correction value.
The invention provides an optimal power dispatching analysis formula which fully considers an optimal power dispatching functionFirst->Maximum cost of the individual power distribution paths +.>In->Maximum power transmission amount selected on the route +.>First->Minimum cost of the individual power distribution paths +.>In->Minimum power transmission amount selected on the route +.>Power supply weight->Total power demand capacity->Total power capacity provided->Lagrangian multiplier->Optimal power function correction value ∈>According to the interaction between the power supply weight and the total power demand capacity and the function, a functional relation is formed By->Maximum selected on pathPower transmission amount and->The interaction relation of the minimum cost of each power distribution path ensures that the data is accurate, performs data dimension reduction, extracts the total power demand capacity, and generates an optimal power scheduling function by utilizing Lagrangian multipliers and the total power capacity>The data redundancy is reduced under the condition of ensuring the accuracy of the data, the calculation force is saved, the calculation is enabled to achieve rapid convergence, and the correction value is corrected by the optimal power function +.>And the optimal circuit allocation is adjusted, so that an optimal power scheduling function is generated more accurately, and the accuracy and reliability of optimal power scheduling are improved. Meanwhile, parameters such as Lagrangian multipliers, power supply weights, optimal power function correction values and the like in the circuits in the formula can be adjusted according to actual conditions, so that the method is suitable for different circuit scheduling scenes, and applicability and flexibility of the algorithm are improved.
Preferably, step S7 comprises the steps of
Step S71: carrying out electric load test processing on intelligent power grid data of the cloud platform so as to obtain the maximum load capacity of the power grid;
step S72: performing simulated power injection processing on a preset power path in the cloud platform by utilizing the optimal power distribution path data to obtain a simulated power injection path;
Step S73: and performing power comparison processing on the simulated power injection path and the maximum load of the power grid, removing the simulated power injection path larger than the maximum load of the power grid, and generating an optimal power distribution path.
According to the method, the intelligent power grid data of the cloud platform are subjected to power load test processing so as to obtain the maximum load capacity of the power grid, so that the accuracy of analysis on the result of the maximum load capacity of the power grid can be improved, and the maximum load capacity of the power grid which can be born in practical application is evaluated so as to prevent faults such as overload and short circuit; the optimal power distribution path data is utilized to perform simulated power injection processing on a preset power path in the cloud platform, so that a simulated power injection path is obtained, better adjustment of a power distribution strategy can be facilitated, the rated power of a transmission line and equipment is ensured not to be exceeded, and the power performance characteristics are improved; and carrying out power comparison processing on the simulated power injection path and the maximum load of the power grid, removing the simulated power injection path larger than the maximum load of the power grid, generating an optimal power distribution path, improving the speed of data storage and processing, removing the path exceeding the maximum load of the power grid, and reducing possible errors of actual power distribution scheduling.
In the embodiment of the invention, intelligent power grid data of a cloud platform are collected, the data are converted into json, csv, csv format and the like, a machine learning algorithm is used for analyzing the converted intelligent power grid data, a future load peak value is predicted so as to generate a power grid maximum load amount, a preset power path is determined through an optimal power distribution path, power injection is carried out on preset power path nodes, the power injection comprises selecting path nodes to carry out power injection and control the size of injected power capacity, the power is injected into each node according to the optimal power distribution path, an analog power injection path is obtained, the power injection condition of each node is accumulated to obtain the power consumption of the whole power grid, the total power consumption of the power grid is compared with the power grid maximum load amount, if the total power consumption of the power grid is smaller than or equal to the power grid maximum load amount, the current scheme is feasible, otherwise, the paths with loads larger than the power grid maximum load amount in the power injection path need to be removed, and the power distribution path is not feasible, the power injection quantity of the nodes can be increased or the paths need to be adjusted, when the total power consumption is smaller than or equal to the maximum load amount, the power distribution path is indicated to be feasible, and the power distribution path is enabled.
The beneficial effects of the invention are that by acquiring the intelligent power grid data in the cloud platform, as the intelligent power grid data is too redundant, therefore, the required power resource data and the regional modeling information need to be extracted to perform model training processing in the initial regional power distribution model to obtain a three-dimensional regional power distribution model, the model can intuitively see the regional power condition, and in order to facilitate data processing, therefore, the three-dimensional mapping process is carried out on the electric power distribution characteristic texture map, the three-dimensional points are mapped onto the two-dimensional image, the readability and the definition of data are improved, the mirror symmetry registration algorithm is utilized to carry out mirror image overturning on the electric power distribution characteristic texture map to obtain an overturning characteristic texture map, the electric power distribution characteristic texture map and the overturning characteristic texture map are overlapped to obtain an electric power overlapped image with a closed characteristic, the result is more accurate, the electric power overlapped image is subjected to image cutting process, the calculation time and the calculation time are saved, the load pressure of a system is reduced, and then edge cutin detection process is carried out on an electric power overlapped image block, thereby more accurately searching the size characteristics of the power flow direction, saving a large amount of resources, preprocessing the horny data of the power image, reducing the influence caused by useless, redundant and abnormal data, then carrying out logistic regression processing to obtain regression curve data, training the power regression data by a decision tree to generate different schemes under different decisions, so as to cope with various subsequent situations possibly occurring in the power distribution process, improve the safety of power distribution, utilize a power prediction model to perform power prediction, find out the optimal power distribution path under different conditions, and improve the utilization rate and stability of power. Therefore, the intelligent power grid resource scheduling and distributing method of the cloud platform can microscopically and carefully analyze the power flow direction of the area, and autonomously schedule and distribute resources under different power conditions through the power prediction model, so that the problems of complicated manual steps and power measurement precision loss are saved.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (1)
1. A cloud platform-based smart grid resource scheduling and distributing method, which is characterized by comprising the following steps:
step S1: acquiring intelligent power grid data of a cloud platform, importing the intelligent power grid data into a pre-constructed initial regional power distribution model for model training processing, generating a regional power distribution model, mapping the regional power distribution model, and generating a power distribution characteristic texture map;
Step S2: performing image superposition registration processing on the electric power distribution characteristic texture map by using a mirror symmetry registration algorithm to generate an electric power superposition image, and performing image cutting processing on the electric power superposition image to obtain an electric power superposition image block;
step S3: performing edge cutin detection processing on the electric power superposition image block to obtain electric power image cutin data; carrying out data preprocessing on the electric power image cutin data to generate standard electric power cutin data;
step S4: performing feature extraction processing according to standard electric power cutin data to generate electric power feature sensitive data; carrying out electric power data logistic regression processing on the electric power characteristic sensitive data by utilizing a logistic regression algorithm to obtain electric power regression data;
step S5: carrying out power decision training on the power regression data through a decision tree model to generate a power prediction model;
step S6: carrying out optimal power behavior prediction on the power distribution data through a power prediction model so as to obtain optimal power distribution path data;
step S7: performing dynamic simulation power injection processing on the optimal power distribution path data to generate an optimal power distribution path;
step S1 comprises the steps of:
s11, acquiring intelligent power grid data of a cloud platform, and identifying and processing the intelligent power grid data in a pre-constructed regional power distribution model to acquire two-dimensional grid elements; step S12: performing three-dimensional discretization on the two-dimensional grid elements so as to generate three-dimensional view discrete points; step S13: performing view aggregation treatment on the three-dimensional view discrete points to obtain a three-dimensional view aggregation image; step S14: carrying out intelligent power grid historical data training processing on the three-dimensional view aggregated image to generate a regional power distribution model; step S15: performing laser point cloud projection processing on the regional power distribution model by using a homogeneous coordinate system so as to generate a power distribution characteristic texture map;
Step S2 comprises the steps of:
step S21: mirror symmetry registration algorithm is utilized to carry out mirror symmetry processing on the electric power distribution characteristic texture map, and an electric power distribution mirror image view is generated; step S22: generating an electric power distribution superposition view by superposition contrast processing of the electric power distribution mirror image view and the electric power distribution characteristic texture map; step S23: performing binarization processing on the electric power distribution superposition view to generate an electric power distribution superposition binary image; step S24: carrying out image data noise reduction processing on the electric power distribution superposition view to obtain a noise reduction electric power distribution diagram; step S25: carrying out electric power distribution image cutting processing on the electric power distribution enhancement map to generate an electric power superposition image block;
step S3 comprises the steps of:
step S31: performing edge line crack detection screening treatment by using a preset crack and crack value and an electric superposition image block, and removing the electric superposition image block smaller than the crack and crack value so as to generate a standard electric superposition image; step S32: performing cutin detection on the standard electric power superposition image by using a corner detection algorithm to generate an electric power superposition binary feature vector; step S33: carrying out Hamming distance matching processing on the electric power superposition binary feature vector to generate electric power image cutin data; step S34: carrying out data feasibility filtering processing on the electric power image cutin data to generate filtered electric power image data; carrying out data cleaning on the filtered power image cutin data to generate cleaning and filtering image data; gray value processing is carried out on the cleaning and filtering image data to obtain standard electric power cutin data;
Step S4 comprises the steps of:
step S41: carrying out principal component analysis processing on standard electric power cutin data to obtain electric power distribution characteristic data; step S42: vector decomposition processing is carried out on the power distribution characteristic data to generate a power distribution characteristic vector; step S43: carrying out space construction processing on the power distribution feature vector by utilizing a covariance matrix algorithm to generate a power distribution feature space; step S44: carrying out space mapping processing on the power grid resource data in the power distribution characteristic space to obtain power characteristic sensitive data; step S45: carrying out logistic regression processing on the power characteristic sensitive data according to a logistic regression algorithm to generate power regression data;
step S5 comprises the steps of:
step S51: performing data comparison processing on the electric power regression data and a preset electric power threshold, marking the electric power regression data as high-risk grade electric power data when the electric power regression data is larger than the electric power threshold, and marking the electric power regression data as common grade electric power data when the electric power regression data is smaller than the electric power threshold; step S52: carrying out decision training processing on the high-risk level power data by utilizing a decision tree model, generating an emergency power signal when the power regression data is the high-risk level power data, and generating a normal power signal when the power regression data is the common level power data; step S53: when the decision tree model acquires an emergency power signal, a high-risk power scheme is generated, and when the decision tree model acquires a normal power signal, a common power scheme is generated; step S54: carrying out power prediction training on the high-risk power prediction scheme and the common power prediction scheme to generate a power prediction model;
Step S6 includes the steps of:
step S61: acquiring power distribution data, and performing historical data collection on the power distribution data to generate historical power distribution data; step S62: according to the power prediction model, carrying out power path analysis processing on the historical power distribution data through a power distribution path formula to generate a power distribution path; step S63: carrying out path optimal analysis on the power distribution path by utilizing an optimal power dispatching analysis formula to obtain optimal power distribution path data;
the power distribution path formula in step S62 is as follows:
in the method, in the process of the invention,expressed as node +.>Power distribution path at->Expressed as node +.>Voltage at>Expressed as the total impedance of the power system, +.>Denoted as +.>Short-circuit capacity on a line, +.>Denoted as +.>Phase angle on line, +.>Represented as on the power distribution pathIs, ">Expressed as the number of resistors between all nodes, +.>Expressed as the +.>Charge capacity of the track current, ">Expressed as the potential difference between all nodes, +.>Expressed as the energy value in the circuit, +.>Represented as the power pressure value in the circuit distribution path, < >>A circuit distribution abnormality adjustment value expressed as generated from a power pressure value in a circuit distribution path and an energy value in a circuit;
The optimal power schedule analysis formula in step S63 is as follows:
in the method, in the process of the invention,is an optimal power scheduling function,/->Denoted as +.>Maximum cost of the individual power distribution paths +.>Is indicated at->Maximum power delivery selected on the path, +.>Denoted as +.>Minimum cost of the individual power distribution paths, +.>Is indicated at->Minimum power delivery on the path, < >>Expressed as power supply weight->Expressed as total required capacity of power,/->Expressed as total power capacity provided, +.>Represented as Lagrangian multiplier for limiting the scheme +.>Deviation between the total transport capacity of all paths and the required capacity, < >>Expressed as an optimal power function correction value;
step S7 includes the steps of:
step S71: carrying out electric load test processing on intelligent power grid data of the cloud platform so as to obtain the maximum load capacity of the power grid;
step S72: performing simulated power injection processing on a preset power path in the cloud platform by utilizing the optimal power distribution path data to obtain a simulated power injection path;
step S73: and performing power comparison processing on the simulated power injection path and the maximum load of the power grid, removing the simulated power injection path larger than the maximum load of the power grid, and generating an optimal power distribution path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310533532.0A CN116258282B (en) | 2023-05-12 | 2023-05-12 | Smart grid resource scheduling and distributing method based on cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310533532.0A CN116258282B (en) | 2023-05-12 | 2023-05-12 | Smart grid resource scheduling and distributing method based on cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116258282A CN116258282A (en) | 2023-06-13 |
| CN116258282B true CN116258282B (en) | 2023-07-21 |
Family
ID=86688344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310533532.0A Active CN116258282B (en) | 2023-05-12 | 2023-05-12 | Smart grid resource scheduling and distributing method based on cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116258282B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116865258B (en) * | 2023-07-14 | 2023-12-05 | 国网冀北电力有限公司电力科学研究院 | Hierarchical distributed power supply intelligent power grid construction method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335752A (en) * | 2015-09-18 | 2016-02-17 | 国网山东省电力公司菏泽供电公司 | Principal component analysis multivariable decision-making tree-based connection manner identification method |
| CN113853624A (en) * | 2019-06-21 | 2021-12-28 | 西门子股份公司 | Method and device for predicting power load data and storage medium |
| CN111612231B (en) * | 2020-05-13 | 2023-09-01 | 云南电网有限责任公司电力科学研究院 | Distribution network line re-jump model fusion processing method and device |
| CN113112099A (en) * | 2021-05-14 | 2021-07-13 | 国网河北省电力有限公司经济技术研究院 | Power grid daily electric quantity prediction model training method and power grid daily electric quantity prediction method |
| CN113496262B (en) * | 2021-09-08 | 2022-02-08 | 山东大学 | Data-driven active power distribution network abnormal state sensing method and system |
| CN113918512A (en) * | 2021-10-22 | 2022-01-11 | 国家电网公司华中分部 | Power grid operation rule knowledge graph construction system and method |
| CN114970362B (en) * | 2022-06-08 | 2023-12-19 | 中交机电工程局有限公司 | Power grid load scheduling prediction method and system under multi-energy structure |
-
2023
- 2023-05-12 CN CN202310533532.0A patent/CN116258282B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 电力系统配网长期电力负荷自动调度方法研究;王军亭;宁静;;自动化与仪器仪表(12);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116258282A (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| US11132551B2 (en) | Systems and methods for skyline prediction for cyber-physical photovoltaic array control | |
| Li et al. | Automatic pavement crack recognition based on BP neural network | |
| CN116258282B (en) | Smart grid resource scheduling and distributing method based on cloud platform | |
| CN113205063A (en) | Visual identification and positioning method for defects of power transmission conductor | |
| CN104504410A (en) | Three-dimensional face recognition device and method based on three-dimensional point cloud | |
| CN110991448A (en) | Text detection method and device for nameplate image of power equipment | |
| CN111582054A (en) | Point cloud data processing method and device and obstacle detection method and device | |
| CN105894041A (en) | Method of extracting substation information in power distribution system based on hyperspectral remote sensing images | |
| CN110414571A (en) | A kind of website based on Fusion Features reports an error screenshot classification method | |
| CN102622753A (en) | Semi-supervised spectral clustering synthetic aperture radar (SAR) image segmentation method based on density reachable measure | |
| CN110766016A (en) | Code spraying character recognition method based on probabilistic neural network | |
| CN111553946A (en) | Method and device for removing ground point cloud and obstacle detection method and device | |
| CN108629809A (en) | A kind of accurate efficient solid matching method | |
| CN113673607A (en) | Method and device for training image annotation model and image annotation | |
| CN114880730A (en) | Method and device for determining target equipment and photovoltaic system | |
| CN110956077A (en) | Method for preventing misoperation and operation safety based on power distribution station room | |
| CN110210561B (en) | Neural network training method, target detection method and device, and storage medium | |
| CN117635630A (en) | Automatic object segmentation method and system based on substation scenic spot cloud | |
| Mahmoudpour et al. | Superpixel-based depth map estimation using defocus blur | |
| Lee et al. | ELF-Nets: deep learning on point clouds using extended laplacian filter | |
| Potnuru et al. | Image processing and machine learning applied for condition monitoring of 11-kV power distribution line insulators using curvelet and LTP features | |
| Zhang et al. | Snow loss modeling for solar modules using image processing and deep learning | |
| Heymann et al. | Explorative ex-ante consumer cluster delineation for electrification planning using image processing tools | |
| CN116630205B (en) | Image processing method, intelligent terminal 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |