CN110955521A - Power distribution network wide area distributed type sinking calculation system and method based on big data - Google Patents
Power distribution network wide area distributed type sinking calculation system and method based on big data Download PDFInfo
- Publication number
- CN110955521A CN110955521A CN201911093205.8A CN201911093205A CN110955521A CN 110955521 A CN110955521 A CN 110955521A CN 201911093205 A CN201911093205 A CN 201911093205A CN 110955521 A CN110955521 A CN 110955521A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- calculation
- node
- data
- primary node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5017—Task decomposition
Abstract
The invention provides a system and a method for calculating wide-area distributed sinking of a power distribution network based on big data, which comprises the following steps: the system comprises a primary node and a plurality of secondary nodes in communication connection with the primary node; the first-level node is used for designing an algorithm according to the service requirement of the power distribution network and sinking the designed algorithm to the second-level node; the secondary nodes are used for decomposing the task of the algorithm according to the association degree of the data source and the service after receiving the algorithm and distributing the decomposed task to a plurality of secondary nodes; and the system is also used for calculating the tasks distributed to the respective decomposed tasks and feeding back the calculation results to the primary node. The invention constructs a two-layer system of a first-level node of wide-area distributed algorithm sinking calculation and a second-level node of local distributed feedback analysis. The problem of online cross-domain rapid parallel computing is solved, and the online computing scale is increased by over 50%.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a power distribution network wide-area distributed sinking calculation system and method based on big data.
Background
Along with the development of a power distribution network, the regional distribution of the power distribution network is expanded, and the service data is increased, so that the power distribution network has the characteristic of natural distribution on the data scale, a large number of interactive energy utilization devices such as distributed power sources and electric vehicles are gathered along with the access of distributed new energy resources, the power distribution network has the attribute of a platform, on the other hand, the data volume of each level of service level is larger and larger, and multidimensional data resources are formed, in the constructed big data resources, the calculation and analysis among data are realized, how to effectively and rapidly calculate and improve the efficiency, how to realize the enhancement of the calculation precision of the data service under the scale of the existing data resources, if implementing fast fusion of algorithms and data parallel computing resources is a prominent problem in the current technology, therefore, it is necessary to change the computing mode from the terminal to the cloud management mode to the cloud to change the mode of the boost distribution network from passive management to active management.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a large data-based wide-area distributed sinking computing system for a power distribution network, which is improved by comprising the following steps: a primary node (1) and a plurality of secondary nodes (2) communicatively connected to the primary node (1);
the primary node (1) is used for designing an algorithm according to the service requirement of the power distribution network and sinking the designed algorithm to the secondary node (2);
the secondary nodes (2) are used for decomposing tasks of the algorithm according to the association degree of the data source and the service after receiving the algorithm, and distributing the decomposed tasks to the plurality of secondary nodes (2); and the system is also used for calculating the tasks distributed to the respective decomposed tasks and feeding back the calculation results to the primary node (1).
In a first preferred embodiment, the improvement is that the primary node (1) includes: the system comprises a data resource definition library (11), an algorithm operator library (12), an online graphical free modeling module (13) and an algorithm encapsulation module (14);
the data resource definition library (11) is used for storing the related service system and service data of the power distribution network;
the algorithm operator library (12) is used for storing big data related algorithms and electric power professional algorithms;
the online graphical free modeling module (13) is used for establishing an algorithm according to the logic of firstly index data and then executing the algorithm according to the service requirement of the power distribution network based on the data resource definition library (11) and the algorithm operator library (12);
the algorithm packaging module (14) is used for packaging the algorithm and sinking the packaged algorithm to a secondary node (2).
In a second preferred technical solution provided by the present invention, the improvement is that the primary node (1) further includes: a result analysis module (15) and a visual component library (16);
the result analyzing module (15) is used for analyzing the calculation result fed back by the secondary node (2);
the visual component library (16) is used for carrying out visual display according to the calculation result analyzed by the result analysis module (15).
The third preferred technical solution provided by the present invention is improved in that the secondary node (2) includes: the system comprises an algorithm analysis module (21), a parallel distributed computation scheduling module (22) and a result encapsulation module (23);
the algorithm analysis module (21) is used for analyzing the sinking algorithm of the primary node (1) and positioning and capturing data needing to be supported in the calculation process of the algorithm;
the parallel distributed computing scheduling module (22) is used for decomposing computing tasks corresponding to the algorithm into a plurality of secondary nodes (2); the computing task is also used for computing the computing task;
and the result packaging module (23) is used for packaging and packaging the calculation result of the parallel distributed calculation scheduling module (22) and feeding back the result to the primary node (1).
In a fourth preferred embodiment of the present invention, the improvement is that the parallel distributed computation scheduling module (22) includes: the system comprises a task scheduling unit and a calculating unit;
the task scheduling unit is used for decomposing the calculation tasks corresponding to the algorithm into a plurality of secondary nodes (2) according to the logic and the corresponding tasks of the algorithm and the association degree between the data and the power distribution network service;
and the computing unit is used for computing the computing task based on a distributed parallel computing mode.
Based on the same invention concept, the invention also provides a power distribution network wide area distributed sinking calculation method based on big data, and the improvement is that the method comprises the following steps:
the primary node (1) designs an algorithm according to the service requirement of the power distribution network, and sinks the designed algorithm to the secondary node (2);
after the secondary nodes (2) receive the algorithm, the algorithm is subjected to task decomposition according to the association degree of the data source and the service, and the decomposed tasks are distributed to the plurality of secondary nodes (2);
each secondary node (2) calculates the task after being distributed to each secondary node and feeds back the calculation result to the primary node (1);
wherein the primary node (1) is in communication connection with a plurality of secondary nodes (2).
The fifth preferred technical solution provided by the present invention is improved in that the first-level node (1) designs an algorithm according to the service requirement of the power distribution network, and sinks the designed algorithm to the second-level node (2), and the method includes:
the primary node (1) establishes an algorithm according to the logic of firstly index data and then executing the algorithm according to the service requirement of the power distribution network based on a data resource definition library (11) and an algorithm operator library (12);
and packaging the algorithm, and sinking the packaged algorithm to a secondary node.
The improvement of the sixth preferred technical solution provided by the present invention is that after the secondary node (2) receives the algorithm, the task corresponding to the algorithm is decomposed into a plurality of secondary nodes (2), and the method includes:
the secondary node (2) analyzes the sinking algorithm of the primary node (1), and positions and captures data to be supported in the calculation process of the algorithm;
decomposing the computational tasks corresponding to the algorithm into a plurality of said secondary nodes (2).
The improvement of the seventh preferred technical solution provided by the present invention is that, each secondary node (2) calculates the decomposition task assigned to it and feeds back the calculation result to the primary node (1), including:
each secondary node (2) is provided with a big data platform (3) of the secondary node (2) to carry out demand type calculation together in a distributed parallel calculation mode;
and the secondary node (2) packages and packs the calculation result and feeds the calculation result back to the primary node (1).
In an eighth preferred embodiment, the improvement of the demand calculation includes:
step 10-1: performing logical processing on the algorithm according to the calculation requirements of the corresponding services to obtain the requirement support indexes of the services corresponding to the algorithm, and designing a logical calculation rule according to the calculation requirements;
step 10-2: according to the logic calculation rule, decomposing a demand support index related to the calculation demand and positioning the demand support index;
step 10-3: judging the type of the demand support index: if the index is a calculation index, performing index decomposition on the calculation index, drilling sub-indexes, and turning to the step 8-2; if the basic index is the basic index, entering a step 8-4;
step 10-4: aiming at the basic indexes, carrying out data positioning;
step 10-5: mining calculation is carried out on data obtained by data positioning;
step 10-6: and performing aggregation calculation on the mining calculation result to obtain a demand type calculation result.
The ninth preferred technical solution provided by the present invention is improved in that after the feedback of the calculation result to the primary node (1), the method further includes:
and the primary node (1) visually displays the calculation result.
The tenth preferred technical solution provided by the present invention is improved in that the step of visually displaying the calculation result by the primary node (1) includes:
the primary node (1) analyzes a calculation result fed back by the secondary node (2);
and carrying out visual display according to the analyzed calculation result.
Compared with the closest prior art, the invention has the following beneficial effects:
1. the invention provides a system and a method for calculating wide-area distributed sinking of a power distribution network based on big data, which comprises the following steps: the system comprises a primary node and a plurality of secondary nodes in communication connection with the primary node; the first-level node is used for designing an algorithm according to the service requirement of the power distribution network and sinking the designed algorithm to the second-level node; the secondary nodes are used for decomposing the task of the algorithm according to the association degree of the data source and the service after receiving the algorithm and distributing the decomposed task to a plurality of secondary nodes; and the system is also used for calculating the tasks distributed to the respective decomposed tasks and feeding back the calculation results to the primary node. The invention constructs a two-layer system of a first-level node of wide-area distributed algorithm sinking calculation and a second-level node of local distributed feedback analysis. The problem of online cross-domain rapid parallel computing is solved, and the online computing scale is increased by over 50%.
2. And (3) constructing an algorithm encapsulation analysis model of the causal association modeling-relation data extraction of the algorithm among the nodes. Downwards, performing cross-domain analysis and distribution on service logic in the algorithm, matching various algorithms, and performing parallel computation; and upwards, carrying out normalized logic calculation on the calculation results of each demand algorithm, and packaging and uploading the results through the nodes. The difficult problem that the multi-source data correlation calculation process is complicated is solved, and the online calculation efficiency is improved by more than 30%.
Drawings
Fig. 1 is a schematic diagram of a wide-area distributed sinking computing system of a power distribution network based on big data according to the present invention;
FIG. 2 is a schematic diagram of a wide-area distributed sinking computing system of a power distribution network based on big data according to the present invention;
fig. 3 is a schematic flow chart of a large data-based wide-area distributed convergence calculation method for a power distribution network according to the present invention;
fig. 4 is a schematic diagram of a node calculation flow in the power distribution network wide area distributed convergence calculation method based on big data provided by the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
The algorithm is applied to all levels of the large data platforms, data resources, storage resources and calculation resources of all levels of the large data platforms are shared, the problem in the cross-domain calculation process is solved, the algorithm is decomposed, cross-domain distributed parallel calculation is carried out, the problem of calculation accuracy is solved, an autonomous intelligent distribution network intelligent prejudgment technology is achieved through fusion of an artificial intelligence algorithm and a professional algorithm, and the power supply service command early warning and analysis capability is improved. The big data platforms at all levels take China as an example and comprise big data platforms from headquarters to provinces.
Example 1:
the invention provides a big data-based power distribution network wide-area distributed convergence calculation system, which is shown in figure 1 and comprises the following components:
a primary node 1 and a plurality of secondary nodes 2 communicatively connected to the primary node 1;
the primary node 1 is used for designing an algorithm according to the service requirement of the power distribution network and sinking the designed algorithm to the secondary node 2;
the secondary nodes 2 are used for decomposing the task of the algorithm according to the association degree of the data source and the service after receiving the algorithm and distributing the decomposed task to the plurality of secondary nodes 2; and the system is also used for calculating the tasks distributed to the respective decomposed tasks and feeding back the calculation results to the primary node 1.
Specifically, the invention provides a schematic diagram of a power distribution network wide-area distributed sinking computing system principle based on big data.
Wherein, the primary node 1 includes: the system comprises a data resource definition library 11, an algorithm operator library 12, an online graphical free modeling module 13 and an algorithm packaging module 14;
the data resource definition library 11 is used for storing the relevant service systems and service data of the power distribution network;
the algorithm operator library 12 is used for storing big data related algorithms and electric power professional algorithms;
the online graphical free modeling module 13 is used for establishing an algorithm according to the logic of firstly index data and then executing the algorithm based on the data resource definition library 11 and the algorithm operator library 12 according to the service requirements of the power distribution network;
and the algorithm packaging module is used for packaging the algorithm and sinking the packaged algorithm to the secondary node 2.
The primary node 1 further includes: a result analysis module 15 and a visual component library 16;
the result analysis module 15 is used for analyzing the calculation result fed back by the secondary node 2;
and the visual component library 16 is used for visually displaying the calculation result analyzed by the result analysis module 15.
Wherein, the secondary node 2 includes: an algorithm analysis module 21, a parallel distributed computation scheduling module 22 and a result encapsulation module 23;
the algorithm analysis module 21 is used for analyzing the algorithm of the sinking of the primary node 1 and positioning and capturing data needing to be supported in the calculation process of the algorithm;
the parallel distributed computing scheduling module 22 is used for decomposing the computing tasks of the corresponding algorithms into a plurality of secondary nodes 2; the system is also used for calculating the calculation task;
and the result packaging module 23 is configured to package and package the calculation result of the parallel distributed calculation scheduling module 22, and feed back the result to the first-level node 1.
The parallel distributed computation scheduling module 22 includes: the system comprises a task scheduling unit and a calculating unit;
the task scheduling unit is used for decomposing the calculation tasks corresponding to the algorithm into a plurality of secondary nodes 2 according to the logic of the algorithm and the corresponding tasks and the association degree between the data and the power distribution network service;
and the computing unit is used for computing the computing task based on a distributed parallel computing mode.
Example 2:
based on the same invention concept, the invention also provides a power distribution network wide area distributed convergence calculation method based on the big data, and as the principle of solving the technical problems of the devices is similar to the power distribution network wide area distributed convergence calculation structure based on the big data, repeated parts are not repeated.
A power distribution network wide area distributed convergence calculation method based on big data comprises the following steps:
step 1: the primary node 1 designs an algorithm according to the service requirement of the power distribution network, and sinks the designed algorithm to the secondary node 2;
step 2: after the secondary nodes 2 receive the algorithm, the algorithm is subjected to task decomposition according to the data source and the service association degree, and the decomposed tasks are distributed to the plurality of secondary nodes 2;
and step 3: each secondary node 2 calculates the task distributed to each secondary node after decomposition, and feeds back the calculation result to the primary node 1;
wherein, the primary node 1 is connected with a plurality of secondary nodes 2 in a communication way.
Specifically, the power distribution network wide-area distributed convergence calculation method based on big data comprises the following steps:
step 101, establishing two-level nodes, wherein the first-level node 1 is an algorithm design and sink node or a wide-area distributed sink computing management node; the secondary node 2 is an algorithm decomposition and calculation feedback node or a local distributed in-situ calculation node;
taking china as an example, a large data center of headquarters is provided with a primary node 1, and a provincial large data center is provided with a secondary node 2.
102, establishing an algorithm operator library 12 of big data related algorithms and electric power professional algorithms at a primary node 1, and defining a receiving input and output relation;
step 103, graphically designing a basic algorithm with freely defined computational logic at the primary node 1 according to business requirements, and realizing fusion and encapsulation with the basic algorithm through the calculation processes of designing the basic algorithm, extracting a big data analysis algorithm and a power grid professional support algorithm in the algorithm designing process;
104, performing parallel distributed sinking on the packaged algorithm to a second-level node 2; monitoring, analyzing and controlling the universe node through the wide-area distributed architecture logic;
105, the secondary node 2 receives the algorithm, analyzes the algorithm logic, and positions and captures data needing to be supported in the calculation process;
step 106, simultaneously carrying out internal computation task scheduling on the positioned data according to computation logic and tasks, dividing the computation task into a plurality of operators according to the association degree between the data source and the service, establishing a causal relationship between an algorithm and the service according to the association degree, and carrying out distributed parallel computation; the secondary node 2 shares the data analysis function of each example and can bear the requirements of scale service expansion and calculation;
step 107, performing logic internal fusion calculation on each calculation process by algorithm distributed calculation to achieve the required result of the calculation task;
and 108, performing feedback verification on the calculation task, and uploading the calculation task to the primary node 1.
Example 3:
the embodiment provides a specific embodiment of a large data-based power distribution network wide-area distributed convergence calculation method, as shown in fig. 2, including:
step 201: combing the service system and the service data at the primary node 1, and establishing an index data resource definition library 11;
step 202: respectively establishing an algorithm operator library 12 for a power professional algorithm, a statistical analysis algorithm, a machine learning algorithm and the like at the primary node 1;
step 203: aiming at a data source at a primary node 1, a demand algorithm is established in a graphical mode through an online graphical free modeling module 13 according to the logic of firstly indexing data and then executing the algorithm;
step 204: the algorithm is packaged in an algorithm packaging module 14 of the primary node 1, the management node is sunk to the secondary node 2 through sinking calculation, and scheduling management is performed by tracking the algorithm of the secondary node;
step 205: the secondary node 2 receives the sinking algorithm of the primary node 1, analyzes the algorithm in an algorithm analysis module 21, and performs data classification processing;
step 206: in the analysis process, performing demand analysis in the algorithm, judging the calculation logic required by the algorithm, acquiring a data path in the data big data storage resource, and establishing a calculation mode;
step 207: after the calculation requirement is judged, performing calculation task decomposition with the big data center, sharing data resources of the big data center, storage resources in the calculation process, spare ML and other calculation resources, and performing demand calculation by the secondary node 1 and the big data platform 3 together;
step 208: through calculation, the calculation result is packaged and packed in a result packaging module 23;
step 209: the result is fed back upwards and uploaded to the primary node 1 by the secondary node 2, and the primary node 1 receives the calculation result and then carries out result analysis by the result analysis module 15;
and the last-level node 1 realizes the display of the calculation result through the visual component library 16.
The specific process of demand calculation is shown in fig. 4, and includes:
step 301: performing logical processing on specific business calculation requirements, defining a requirement support index of each basic business, and designing a logical calculation rule according to the business calculation requirements;
step 302: according to the calculation rule, resolving indexes related to calculation requirements for positioning;
the index positioning means that indexes are identified and positioned due to different statistical dimensions or services, for example, when one index is related to multi-source services, the index positioning and identification are performed according to algorithm requirements, such as operation data of a certain transformer in a marketing service system and operation data of a transformer in an equipment management system.
Step 303: judging the type of the index by algorithms such as big data, artificial energy and the like; the specifically adopted algorithm comprises: cluster analysis, association degree identification, deviation degree analysis and the like;
step 304: if the index is a calculation type index, performing index decomposition, drilling a sub-index, and repeating the process until the index is a basic type index;
the basic index refers to an index that can be directly obtained, and the calculation index refers to an index that can be obtained only by calculation with the basic index. For example, the power supply amount and the power sale amount are basic indicators, the line loss is a calculation indicator, and the line loss is (power supply amount-power sale amount)/power supply amount.
Step 305: if the index is a basic index, carrying out data positioning;
step 306: mining calculation is carried out on the data, and algorithm distributed parallel calculation is carried out on a decomposition operator;
the distributed parallel computation is divided into two types, wherein 1 is physical distributed computation, and 2 is algorithm decomposition algorithm distributed computation. The physical distribution type is used for improving the calculation efficiency, and the algorithm distribution type is used for improving the algorithm precision. At present, clustering is generally separated from service when large data mining analysis is carried out, so that the algorithm is added in a distributed mode.
Step 307: performing result data result clustering management and performing aggregation calculation;
step 308: and acquiring a calculation demand result.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present application and not for limiting the scope of protection thereof, and although the present application is described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present application, they can make various changes, modifications or equivalents to the specific embodiments of the application, but these changes, modifications or equivalents are all within the scope of protection of the claims to be filed.
Claims (12)
1. A big data-based wide-area distributed settlement computing system for a power distribution network is characterized by comprising: a primary node (1) and a plurality of secondary nodes (2) communicatively connected to the primary node (1);
the primary node (1) is used for designing an algorithm according to the service requirement of the power distribution network and sinking the designed algorithm to the secondary node (2);
the secondary nodes (2) are used for decomposing tasks of the algorithm according to the association degree of the data source and the service after receiving the algorithm, and distributing the decomposed tasks to the plurality of secondary nodes (2); and the system is also used for calculating the tasks distributed to the respective decomposed tasks and feeding back the calculation results to the primary node (1).
2. The system according to claim 1, characterized in that the level one node (1) comprises: the system comprises a data resource definition library (11), an algorithm operator library (12), an online graphical free modeling module (13) and an algorithm encapsulation module (14);
the data resource definition library (11) is used for storing the related service system and service data of the power distribution network;
the algorithm operator library (12) is used for storing big data related algorithms and electric power professional algorithms;
the online graphical free modeling module (13) is used for establishing an algorithm according to the logic of firstly index data and then executing the algorithm according to the service requirement of the power distribution network based on the data resource definition library (11) and the algorithm operator library (12);
the algorithm packaging module (14) is used for packaging the algorithm and sinking the packaged algorithm to a secondary node (2).
3. The system according to claim 1, characterized in that said primary node (1) further comprises: a result analysis module (15) and a visual component library (16);
the result analyzing module (15) is used for analyzing the calculation result fed back by the secondary node (2);
the visual component library (16) is used for carrying out visual display according to the calculation result analyzed by the result analysis module (15).
4. The system according to claim 1, characterized in that the secondary node (2) comprises: the system comprises an algorithm analysis module (21), a parallel distributed computation scheduling module (22) and a result encapsulation module (23);
the algorithm analysis module (21) is used for analyzing the sinking algorithm of the primary node (1) and positioning and capturing data needing to be supported in the calculation process of the algorithm;
the parallel distributed computing scheduling module (22) is used for decomposing computing tasks corresponding to the algorithm into a plurality of secondary nodes (2); the computing task is also used for computing the computing task;
and the result packaging module (23) is used for packaging and packaging the calculation result of the parallel distributed calculation scheduling module (22) and feeding back the result to the primary node (1).
5. The system of claim 4, wherein the parallel distributed computation scheduling module (22) comprises: the system comprises a task scheduling unit and a calculating unit;
the task scheduling unit is used for decomposing the calculation tasks corresponding to the algorithm into a plurality of secondary nodes (2) according to the logic and the corresponding tasks of the algorithm and the association degree between the data and the power distribution network service;
and the computing unit is used for computing the computing task based on a distributed parallel computing mode.
6. A power distribution network wide area distributed convergence calculation method based on big data is characterized by comprising the following steps:
the primary node (1) designs an algorithm according to the service requirement of the power distribution network, and sinks the designed algorithm to the secondary node (2);
after the secondary nodes (2) receive the algorithm, the algorithm is subjected to task decomposition according to the association degree of the data source and the service, and the decomposed tasks are distributed to the plurality of secondary nodes (2);
each secondary node (2) calculates the task after being distributed to each secondary node and feeds back the calculation result to the primary node (1);
wherein the primary node (1) is in communication connection with a plurality of secondary nodes (2).
7. The method of claim 6, wherein the primary node (1) designs an algorithm according to the service requirement of the power distribution network, and sinks the designed algorithm to the secondary node (2), and comprises the following steps:
the primary node (1) establishes an algorithm according to the logic of firstly index data and then executing the algorithm according to the service requirement of the power distribution network based on a data resource definition library (11) and an algorithm operator library (12);
and packaging the algorithm, and sinking the packaged algorithm to a secondary node.
8. The method of claim 6, wherein the secondary node (2), upon receiving the algorithm, decomposes tasks corresponding to the algorithm into a plurality of secondary nodes (2) comprising:
the secondary node (2) analyzes the sinking algorithm of the primary node (1), and positions and captures data to be supported in the calculation process of the algorithm;
decomposing the computational tasks corresponding to the algorithm into a plurality of said secondary nodes (2).
9. The method according to claim 6, wherein said each secondary node (2) performs the calculation of the decomposition tasks assigned to it and feeds back the calculation results to said primary node (1), comprising:
each secondary node (2) is provided with a big data platform (3) of the secondary node (2) to carry out demand type calculation together in a distributed parallel calculation mode;
and the secondary node (2) packages and packs the calculation result and feeds the calculation result back to the primary node (1).
10. The method of claim 9, wherein the demand calculation comprises:
step 10-1: performing logical processing on the algorithm according to the calculation requirements of the corresponding services to obtain the requirement support indexes of the services corresponding to the algorithm, and designing a logical calculation rule according to the calculation requirements;
step 10-2: according to the logic calculation rule, decomposing a demand support index related to the calculation demand and positioning the demand support index;
step 10-3: judging the type of the demand support index: if the index is a calculation index, performing index decomposition on the calculation index, drilling sub-indexes, and turning to the step 8-2; if the basic index is the basic index, entering a step 8-4;
step 10-4: aiming at the basic indexes, carrying out data positioning;
step 10-5: mining calculation is carried out on data obtained by data positioning;
step 10-6: and performing aggregation calculation on the mining calculation result to obtain a demand type calculation result.
11. The method of claim 6, wherein after feeding back the calculation result to the primary node (1), further comprising:
and the primary node (1) visually displays the calculation result.
12. The method of claim 11, wherein the visualization of the computation by the level one node (1) comprises:
the primary node (1) analyzes a calculation result fed back by the secondary node (2);
and carrying out visual display according to the analyzed calculation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093205.8A CN110955521A (en) | 2019-11-11 | 2019-11-11 | Power distribution network wide area distributed type sinking calculation system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093205.8A CN110955521A (en) | 2019-11-11 | 2019-11-11 | Power distribution network wide area distributed type sinking calculation system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110955521A true CN110955521A (en) | 2020-04-03 |
Family
ID=69977123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911093205.8A Pending CN110955521A (en) | 2019-11-11 | 2019-11-11 | Power distribution network wide area distributed type sinking calculation system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110955521A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112261141A (en) * | 2020-10-23 | 2021-01-22 | 移康智能科技（上海）股份有限公司 | Local Internet of things computing power detection system based on block chain technology |
-
2019
- 2019-11-11 CN CN201911093205.8A patent/CN110955521A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112261141A (en) * | 2020-10-23 | 2021-01-22 | 移康智能科技（上海）股份有限公司 | Local Internet of things computing power detection system based on block chain technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107402976B (en) | Power grid multi-source data fusion method and system based on multi-element heterogeneous model | |
| CN104167736B (en) | A kind of bulk power grid parallel network topology analyzing method | |
| CN109408548A (en) | A kind of urban electric power big data application system and method | |
| CN102750406B (en) | Multi-version management method for model set and difference model-based power grid model | |
| CN103605662B (en) | Distributed computation frame parameter optimizing method, device and system | |
| CN109831478A (en) | Rule-based and model distributed processing intelligent decision system and method in real time | |
| CN109241159B (en) | Partition query method and system for data cube and terminal equipment | |
| CN105320757A (en) | Business intelligent analysis method for quickly processing data | |
| CN105467953A (en) | Knowledge representation facing industrial big data and automation application method thereof | |
| CN104424018A (en) | Distributed calculating transaction processing method and device | |
| CN114416855A (en) | Visualization platform and method based on electric power big data | |
| CN108108466A (en) | A kind of distributed system journal query analysis method and device | |
| US11281698B2 (en) | Data configuration query method and device | |
| CN110134507A (en) | A kind of cooperative computing method under edge calculations system | |
| CN112182077A (en) | Intelligent operation and maintenance system based on data middling platform technology | |
| CN108415912A (en) | Data processing method based on MapReduce model and equipment | |
| CN111159897B (en) | Target optimization method and device based on system modeling application | |
| CN109582837A (en) | A kind of visualized data processing method based on cloud and system | |
| CN106445645A (en) | Method and device for executing distributed computation tasks | |
| Mohamed et al. | A review on big data management and decision-making in smart grid | |
| Sbai et al. | A real-time decision support system for big data analytic: A case of dynamic vehicle routing problems | |
| CN110955521A (en) | Power distribution network wide area distributed type sinking calculation system and method based on big data | |
| CN113822585A (en) | Intelligent smelting factory informatization management system | |
| CN113722564A (en) | Visualization method and device for energy and material supply chain based on space map convolution | |
| Gunawardena et al. | Real-time Uber data analysis of popular Uber locations in Kubernetes environment |
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 |