CN109063980A - Memory calculation method and system suitable for electrical network analysis - Google Patents
Memory calculation method and system suitable for electrical network analysis Download PDFInfo
- Publication number
- CN109063980A CN109063980A CN201810777084.8A CN201810777084A CN109063980A CN 109063980 A CN109063980 A CN 109063980A CN 201810777084 A CN201810777084 A CN 201810777084A CN 109063980 A CN109063980 A CN 109063980A
- Authority
- CN
- China
- Prior art keywords
- data
- memory
- power network
- analysis
- grid
- 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
- 238000003012 network analysis Methods 0.000 title claims abstract description 54
- 238000004364 calculation method Methods 0.000 title claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 49
- 238000004088 simulation Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 36
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 30
- 238000013459 approach Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 34
- 238000005516 engineering process Methods 0.000 claims description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims description 3
- 230000008521 reorganization Effects 0.000 claims description 3
- 229910002056 binary alloy Inorganic materials 0.000 claims 1
- 230000008569 process Effects 0.000 description 12
- 238000013461 design Methods 0.000 description 11
- 238000013499 data model Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013332 literature search Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000000819 phase cycle Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the memory calculation methods and system that are suitable for electrical network analysis, comprising: acquisition electric network data；The first power network object model towards power network object is established according to electric network data；The second power network object analysis model of data grids based on memory is established using the first power network object model and memory data grid integrated approach；Electric network data is bound using data affine technolog, to realize efficient access service；The framework that electrical network analysis memory calculates integrally is realized using Enterprise SOA.The present invention alleviates the confinement problems of power grid real-time internal memory database, has cracked " the data I/O bottleneck " of data processing, provides convenience for the simulation analysis calculating of electric system.
Description
Technical field
The present invention relates to technical field of power systems, more particularly, to the memory calculation method for being suitable for electrical network analysis and are
System.
Background technique
From electric system angle, electric system is nonlinear high-order complication system, and data are presented when calculating in simulation analysis
Intensive calculation processing feature.The source of data and storage require interactive with disk in traditional power grid Simulation Software Design,
Therefore implement electric system simulation in large-scale computer cluster environment, the bottleneck of efficiency is usually disk and network data I/
O。
High-performance is online at present and real-time electric power system emulation calculates and mainly uses Distributed Parallel Computing technology, by more
A node handles data simultaneously to alleviate electric system simulation and calculate mass data processing facing challenges.Since these optimize skill
Still based on traditional memory-disk access mode, " the data I/O bottleneck " of data processing still has art, and this kind of scheme is only
It is to improve, mitigate this bottleneck problem.
From computer angle, power grid EMS real-time internal memory database has one limitation at present, i.e., it can only be in unicomputer
It is run on node.At power grid regulation center, EMS real-time internal memory database is run on active and standby computer node, but on main-standby nodes
Memory database be independent operating, system design on not can guarantee main-standby nodes storage consistency on messaging
(consistency)。
Summary of the invention
In view of this, alleviating the purpose of the present invention is to provide the memory calculation method and system that are suitable for electrical network analysis
The confinement problems of power grid real-time internal memory database, have cracked " the data I/O bottleneck " of data processing, are the imitative of electric system
True analytical calculation is provided convenience.
In a first aspect, the embodiment of the invention provides the memory calculation methods for being suitable for electrical network analysis, comprising:
Acquire electric network data；
The first power network object model towards power network object is established according to the electric network data；
The second of data grids based on memory are established using the power network object model and memory data grid integrated approach
Power network object analysis model；
According to the second power network object analysis model, the electric network data is bound using data affine technolog, it is efficient to realize
Access service；
The framework that electrical network analysis memory calculates integrally is realized using Enterprise SOA.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein institute
It states and includes: according to first power network object model of the electric network data foundation towards power network object
Power grid admittance matrix is generated according to the electric network data；
The first power network object model towards bus and branch is generated according to the power grid admittance matrix, wherein institute
State the network topology structure that the first power network object model is directly storage simulation parameter.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein institute
State the second power grid pair that data grids based on memory are established using the power network object model and memory data grid integrated approach
Picture analysis model includes:
Using unicomputer power network object modeling method and open source memory data grid technology, by the power network object model
It carries out integrating the second power network object analysis model with the memory data grid.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the third of first aspect
Possible embodiment, wherein the first power network object model includes power network object and element object, described by the power grid
Object model and the memory data grid carry out integrating the second power network object analysis model
The interface provided using the open source memory data grid technology, to each power network object and the element pair
Key is generated as carrying out serializing, and is distributed and is stored into one or more buffer service nodes automatically according to the key, is made described
Power network object and element object are corresponded by hash function and key, to establish the second power network object analysis mould
Type, wherein the power network object includes bus object, branch object, and the element object includes node object.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein institute
Stating data affine technolog is that the power network object is distributed in memory data grid, has related close for one group by key association
The power network object of system is tied on the same subregion of node, and grid simulation algorithm is executed on the subregion.
The 4th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 5th kind of first aspect
Possible embodiment, wherein described to include: using the data affine technolog binding electric network data
After the power network object and element object serialize the key-value pair to be formed, by the power network object and the element
Object classification is stored in the memory data grid；
When needing the complete power network object to carry out simulation calculation, the key-value pair is subjected to unserializing, again
Organize the formation of the power network object；
On the same subregion, the grid simulation algorithm is executed to the power network object.
With reference to first aspect, the embodiment of the invention provides the 6th kind of possible embodiments of first aspect, wherein institute
The framework for stating the calculating of electrical network analysis memory is encapsulated into simulation algorithm in the form of services on the electrical network analysis model, when outer
When portion requests access to data or processing data, then executes and be stored in the simulation algorithm of the same position with the data to mention
It is serviced for calculating.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 7th kind of first aspect
Possible embodiment, wherein it is described to each power network object and the element object carry out serializing generate key include:
The power network object and the element object are subjected to serializing using power network object model wrapper and are converted into two
Binary form is pushed in the memory data grid in the form of key-value pair.
The 5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 8th kind of first aspect
Possible embodiment, described that the key-value pair is carried out unserializing, reorganization forms the power network object and includes:
Using power network object model wrapper, unserializing, shape are carried out to each key-value pair by functional expression interface
At the power network object.
Second aspect, the embodiment of the invention provides the memory computing systems for being suitable for electrical network analysis, comprising:
Acquisition unit, for acquiring electric network data；
First modeling unit, for establishing the first power network object model towards power network object according to the electric network data；
Second modeling unit, for being established using the power network object model and memory data grid integrated approach based on interior
Second power network object analysis model of deposit data grid；
Data are affine unit, for binding the electric network data using data affine technolog, to realize efficient access service；
Framework realizes unit, for integrally realizing the framework of electrical network analysis memory calculating using Enterprise SOA.
The present invention provides the memory calculation methods and system that are suitable for electrical network analysis, comprising: acquisition electric network data；According to
Electric network data establishes the first power network object model towards power network object；Utilize the first power network object model and internal storage data
Grid integration method establishes the second power network object analysis model of data grids based on memory；According to second power network object point
Model is analysed, electric network data is bound using data affine technolog, to realize efficient access service；Using Enterprise SOA entirety
Realize the framework that electrical network analysis memory calculates.The present invention alleviates the confinement problems of power grid real-time internal memory database, cracks
" the data I/O bottleneck " of data processing is provided convenience for the simulation analysis calculating of electric system.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the memory calculation method flow chart provided in an embodiment of the present invention suitable for electrical network analysis；
Fig. 2 is power network object model schematic provided in an embodiment of the present invention；
Fig. 3 is network uml class figure provided in an embodiment of the present invention；
Fig. 4 is that the electrical network analysis model of data grids based on memory provided in an embodiment of the present invention generates schematic diagram；
Fig. 5 is the realization principle schematic diagram of wrapper provided in an embodiment of the present invention；
Fig. 6 is bus wrapper schematic diagram provided in an embodiment of the present invention；
Fig. 7 is wrapper module overall schematic provided in an embodiment of the present invention；
Fig. 8 is wrapper uml diagram provided in an embodiment of the present invention；
Fig. 9 is electric network data subregion schematic diagram provided in an embodiment of the present invention；
Figure 10 is that key provided in an embodiment of the present invention realizes the affine schematic diagram of data；
Figure 11 is electrical network analysis memory computing architecture provided in an embodiment of the present invention；
Figure 12 is the Distributed-solution figure provided in an embodiment of the present invention based on data/address bus；
Figure 13 is the Distributed-solution figure provided in an embodiment of the present invention based on data grids；
Figure 14 is the scheme schematic diagram of the memory calculation method provided in an embodiment of the present invention suitable for electrical network analysis；
Figure 15 is the memory computing system schematic diagram provided in an embodiment of the present invention suitable for electrical network analysis.
Icon:
10- acquisition unit；The first modeling unit of 20-；The second modeling unit of 30-；40- data are affine unit；50- framework
Realize unit.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
Currently, electric system is nonlinear high-order complication system from electric system angle, simulation analysis is presented when calculating
Data-intensive computing processing feature.The source of data and storage require to hand over disk in traditional power grid Simulation Software Design
Mutually, therefore in large-scale computer cluster environment implement electric system simulation, the bottleneck of efficiency is usually disk and network number
According to I/O.
High-performance is online at present and real-time electric power system emulation calculates and mainly uses Distributed Parallel Computing technology, by more
A node handles data simultaneously to alleviate electric system simulation and calculate mass data processing facing challenges.Since these optimize skill
Still based on traditional memory-disk access mode, " the data I/O bottleneck " of data processing still has art, and this kind of scheme is only
It is to improve, mitigate this bottleneck problem.
From computer angle, power grid EMS real-time internal memory database has one limitation at present, i.e., it can only be in unicomputer
It is run on node.At power grid regulation center, EMS real-time internal memory database is run on active and standby computer node, but on main-standby nodes
Memory database be independent operating, system design on not can guarantee main-standby nodes storage consistency on messaging
(consistency).Based on this, the memory calculation method and system provided in an embodiment of the present invention suitable for electrical network analysis is delayed
The confinement problems for having solved power grid real-time internal memory database have cracked " the data I/O bottleneck " of data processing, are electric system
Simulation analysis calculating is provided convenience.
Embodiment one:
Referring to Fig.1, include: suitable for the memory calculation method of electrical network analysis
Step S101 acquires electric network data；
Step S102 establishes the first power network object model towards power network object according to electric network data；
Step S103 is counted based on memory using the first power network object model and the foundation of memory data grid integrated approach
According to the second power network object analysis model of grid；
Step S104 binds electric network data using data affine technolog according to the second power network object analysis model, to realize
Efficient access service；
Step S105 integrally realizes the framework that electrical network analysis memory calculates using Enterprise SOA.
Further, step S102 includes:
Power grid admittance matrix is generated according to electric network data；
The first power network object model towards bus and branch is generated according to power grid admittance matrix, wherein the first power grid pair
As model is the network topology structure for directly storing simulation parameter.
Further, step S103 includes:
Using unicomputer power network object modeling method and open source memory data grid technology, by power network object model and interior
Deposit data grid carries out integrating the second power network object analysis model.
Principle is as follows: the interface provided using open source memory data grid technology, to each power network object and element object
Carry out serializing and generate key, and be distributed and be stored into one or more buffer service nodes automatically according to key, make power network object and
Element object is corresponded by hash function and key, to establish the second power network object analysis model, wherein power network object
Including bus object, branch object, element object includes node object.
Further, data affine technolog is that power network object is distributed in memory data grid, is associated with by key by one
There is group the power network object of correlativity to be tied on the same subregion of node, and grid simulation algorithm is executed on subregion.
Further, step S104 includes:
After power network object and element object serialize the key-value pair to be formed, power network object and element object classification are saved
In memory data grid；
When needing complete power network object to carry out simulation calculation, key-value pair is subjected to unserializing, reorganizes and is formed
Power network object；
On same subregion, grid simulation algorithm is executed to power network object.
Further, the framework that electrical network analysis memory calculates is that simulation algorithm is encapsulated into electrical network analysis in the form of services
On model, when external request accesses data or processing data, then the simulation algorithm that the same position is stored in data is executed
To provide the service of calculating.
Further, be previously mentioned to each power network object and element object carry out serializing generate key include:
Power network object and element object are subjected to serializing using power network object model wrapper and are converted into binary form,
It is pushed in memory data grid in the form of key-value pair.
Further, what is be previously mentioned carries out key-value pair unserializing, and reorganization forms power network object and includes:
Using power network object model wrapper, unserializing is carried out to each key-value pair by functional expression interface, forms electricity
Net object.
Embodiment two:
To easily facilitate the technical solution for understanding the embodiment of the present invention, an explanation is done to the term being related to:
Electric network data model: Power Network Modeling Method refers in the present embodiment builds in computer system (database or memory)
The related software of the electrical network analysis model such as vertical conductive equipment, measurement object and equipment room connection relationship, device parameter implements skill
Art.Power Network Modeling Method is that the advanced applied analysis calculating of electric system is basic, the key position in on-line security and stability analysis,
It is one of the critical issue for improving on-line security and stability analysis performance study.
Memory computing technique: it is a kind of new approaches for solving large-scale data processing I/O bottleneck problem that memory, which calculates,.Inside
It deposits CPU in calculating and directly reads data from memory rather than on disk, relative to disk, the reading and writing data speed of memory will be higher by
Several orders of magnitude.It saves the data in memory, internal storage data is directly read in calculating process and traditional is accessed from disk
Data are compared, and data processing performance can be greatlyd improve.
Memory calculating be centered on big data, by being reformed to traditional software architecture structure and programming model etc.,
Finally it is obviously improved the novel calculating mode of big data calculation processing performance.Its essence is placed the data in calculator memory
It is directly operated, avoids the migration of data in data processing to greatest extent.After memory calculating mode, data
It stores and transmits the concern core that will replace calculating task and become calculation processing.During memory calculates, data are stored in memory,
Memory traditional in data processing-disk access mode is evaded, several orders of magnitude can be obtained in reading and writing data speed
It is promoted, makes it possible data volume greatly quick real time data processing.
Distributed memory data grids: memory data grid technology is a kind of grid shared towards local area network memory source
Data distribution to multiple buffer service nodes persistent storage and can be managed the technologies of data in memory by system.The technology
Redundancy backup mechanism is provided, realizes that High Availabitity is supported, node can be dynamically added, and bring good, transparent dynamic scalability.It
Main target be improve memory-intensive application or I/O intensive applications system performance.Memory data grid technology can be with
To solve the problems, such as that real-time and the response speed of powernet security and stability analysis provide support technology.
From electric system angle, electric system is nonlinear high-order complication system, and data are presented when calculating in simulation analysis
Intensive calculation processing feature.The source of data and storage require interactive with disk in traditional power grid Simulation Software Design,
Therefore implement electric system simulation in large-scale computer cluster environment, the bottleneck of efficiency is usually disk and network data I/
O。
High-performance is online at present and real-time electric power system emulation calculates and mainly uses Distributed Parallel Computing technology, by more
A node handles data simultaneously to alleviate electric system simulation and calculate mass data processing facing challenges.Since these optimize skill
Still based on traditional memory-disk access mode, " the data I/O bottleneck " of data processing still has art, and this kind of scheme is only
It is to improve, mitigate this bottleneck problem.
From computer angle, power grid EMS real-time internal memory database has one limitation at present, i.e., it can only be in unicomputer
It is run on node.At power grid regulation center, EMS real-time internal memory database is run on active and standby computer node, but on main-standby nodes
Memory database be independent operating, system design on not can guarantee main-standby nodes storage consistency on messaging
(consistency)。
The key technology point being related to technical solution of the embodiment of the present invention is illustrated below.
1, the power network object modeling of object-oriented
Object-oriented (Object-oriented, OO) method is common general software modeling and development approach, general packet
Include object oriented analysis (OOA), object oriented designing (OOD), object-oriented programming (OOP) etc., formed modeling,
The reusable bases of each rank such as design, realization.
Common Power System Analysis algorithm is based on power grid admittance [Y] matrix, therefore the electric power of the present embodiment discussion
System model belongs to power grid bus/branch model class.In grid simulation, power grid can be indicated with object model.It is shown in Fig. 2
Power network object model in, network, bus, branch class relationship can map grid simulation analysis in [Y] matrix branch node
Incidence relation.In this model, bus object is one " node ", can connect one group of branch object.Branch object is one
It is attached between two bus objects " side " there are two terminal.Network object is a container, median generatrix and branch object
It can be defined, branch object can be connected on these bus objects, form a network for grid simulation analysis
Topological structure.The specific simulation parameter of power grid can be stored directly in corresponding object, and then formation can be used for power grid and imitate
The object model really analyzed.
In the power network modeling and program development practice using object-oriented, grid simulation problem can be divided into multiple pumpings
As conceptual level, such as network, Load flow calculation network, as shown in Figure 3.5 kinds of network class definition and inheritance are illustrated in figure:
1) Network class: include network topological information, be the base class of various network models below；2) Aclf Network class: comprising just
The information and Load flow calculation information of sequence network Y matrix；3) Acsc Network class: including negative phase-sequence, zero-sequence network Y matrix and short circuit
Calculate information；4) Dist Network class: include distribution system analysis information, usually describe electricity with name plate rating in distribution system analysis
Net equipment；5) DStability Network class: including Power Network Transient Stability artificial intelligence.Pass through Similar integral, extended network class
Definition, can study wider grid simulation problem analysis.
We learn from the Development Practice of open source power system simulation software system InterPSS [5], using towards right
Many benefits can be brought by carrying out grid simulation modeling and program development as method: 1) mathematical model can be expressed as towards right
The conceptual model of elephant to software design and is opened mathematical concept Model Transfer in the way of succinct, complete, accurate, intelligible
Hair personnel；2) it is easy to use executing model drive structure (MDA-Model Driven Architecture) design method, it will
Mathematical concept auto-building model specific implementation model and object identification code, model are set to the movable center of software development；3) it ties
Specific implementation and object identification code are closed, numerical computation method is embodied as to the algorithm independently decoupled, implementation model and algorithm separate；4)
Using the software development methodology of object-oriented, it can make that software configuration is clear, has good encapsulation, good easily extension
Property, and reuse of code is high.
Grid simulation analysis in, electric network model and calculate data will finally be loaded (Load) to calculator memory into
Row calculates analysis.Thus, power grid calculator memory implementation model (Implementation Model) is to support quickly online point
One of the critical issue of the power network modeling research of analysis.Open source power system simulation software system InterPSS is concerned only in separate unit meter
Grid simulation analysis memory object modeling in calculation machine list CPU environment, and big data analysis is usually in a distributed computing environment
It is parallel to carry out.By literature search, it has not been found that have this respect research work report, thus in multi -CPU/Core distribution meter
Calculate the important content of grid simulation analysis memory object modeling problem the present embodiment research in environment.
2, the power system simulation model in memory data grid
Using the dynamic extensibility of memory data grid, high availability and to the good support of object data model
Property, electrical network analysis data model is constructed, in memory data grid to support the inward-facing electrical network analysis for depositing calculating mode to calculate
Structure system.We have existing unicomputer power network object modeling method and open source memory data grid technology Hazelcast
Machine combines, and power network object modeling method is generalized to distributed memory data grids.As shown in figure 4, a power network object model
Be made of a group objects (such as bus object, branch object), memory data grid technology provide interface can by power network object with
And wherein numerous element objects (node object, branch object etc.) are corresponded by hash function and " key " (Key), it is each
According to " key ", one or more buffer service nodes are arrived in distribution (storage) to object automatically after serializing, thus in internal storage data
The complete electrical network analysis data model for supporting memory to calculate is generated in grid.
As shown in figure 5, power network object model wrapper (Wrapper) is can to serialize power network object model,
And can mutually be converted between binary form and object form, it is final to realize single machine power network object model and based on interior
The module of the interaction of the electric network model of deposit data grid.Wrapper is the core of the present embodiment technology, will directly affect entire number
According to the performance of model.
1) binary form value is converted by all component object models serializing of certain class (such as Bus, Branch),
And it is pushed in the distributed container IMap of distributed memory data grids offer and (incites somebody to action in the form of key-value pair (key, value)
All component object models carry out serializing and are stored in centralized container Map, then are pushed to distribution using the method for batch processing
Formula memory data grid, this mode are more efficient)；
2) unserializing is carried out to each key-value pair for meeting setting by functional expression interface Predicate, forms element
Object model is simultaneously associated, and ultimately forms power network object model.
By taking bus wrapper Bus Wrapper as an example, such as Fig. 6, bus wrapper one by one by state in all bus objects,
The data sequences such as number, title, busbar voltage bound and reference voltage chemical conversion binary form, that is, Bus object 1->
Value1, Bus object 2-> value2, Bus object 3-> value3, and assign each value one specifically
" key " formation key-value pair, i.e. value1-> (elementKey1, value1), value2-> (elementKey2,
Value2), value3-> (elementKey3, value3).Key-value pair is stored in the Bus IMap of memory data grid.
It include different types of element object in electric network data model, different element objects is carried out by corresponding wrapper
Processing, the entirety of wrapper is as shown in fig. 7, when all elements are disposed, and all element objects of power network object are with key assignments
Pair form be stored in a series of IMap container.Data are converted to key-value pair form on the right of figure from figure left side object form,
Mean that the power network object model modeling of data grids based on memory is completed, data constantly save in memory.When having needed
When whole electric network data model, generate to form power network object model just and can be carried out electric system simulation meter using wrapper unserializing
It calculates, i.e., data is converted to from figure the right key-value pair form by figure left side object form by wrapper, it is suitable to generate object model
In the resolving of all related key-value pairs.In this process, wrapper first will each key assignments relevant to the electric network
Component object model is formed to unserializing is carried out, and provided according to the related information saved in key-value pair by InterPSS
API re-establishes the association between element object, and (such as two buses connected according to branch object are numbered, by branch object
It is associated with two bus objects being connect), ultimately form electric network object model.
Consider the physical meaning of the data of power grid and the expansion of module, Fig. 8 is the present embodiment wrapper main body breviary
Uml diagram, all object encapsulation devices, which are realized, inherits IElem Cache Wrapper interfaces, primarily to illustrating wrapper API
Realization situation.By taking Branch wrapper as an example: 1) Abstract Elem Cache Wrapper is abstracted element wrapper class,
Major function includes that serializing and unserializing processing are carried out to the essential attribute of universal component object, additionally relates to wrapper
Lowermost layer design, such as all main time-consuming process are all made of the method (for/foreach) of parallel processing；2)
Networked Element Cache Wrapper network element wrapper class, major function includes to element and network object
Relationship carry out serializing and unserializing processing；3) Abstract Branch Cache Wrapper is abstracted branch wrapper
Class, major function include carrying out serializing and antitone sequence to the particular attribute and branch object of branch and the relationship of bus object
Change processing；4) Aclf Branch Cache Wrapper stable state branch wrapper, major function are to integrate all parent methods to incite somebody to action
Two methods that branch data model mutually converts between key-value pair and object form.
3, data are affine
The application efficiency of memory data grid technology depends on Data processing cost on network communication.With most basic trend
For calculating, when storing certain Load flow calculation case data in memory data grid, it is intended that by the relevant object of this group
It is stored in the same subregion of calculate node (Partition), is generated in simulation analysis to avoid this calculating case unnecessary
Internodal data migration realizes that the big data memory of so-called " moving algorithm is without mobile data " calculates theory.According to memory
Calculating theory, grid simulation parser (such as Load flow calculation algorithm) will be pushed to data storage calculating in calculating process
It is executed on node.If all object datas are stored on same calculate node subregion such as a certain Load flow calculation case of Fig. 9,
Load flow calculation algorithm also executes on this node simultaneously, and there is no need to obtaining number in other calculate nodes in calculating process
According to.The data distribution plan of so-called " data according to data grids are distributed in needed for calculating " in big data analysis processing
Slightly.
Usual memory data grid technology all provides data affine (Data Affinity) function, allows user by one group
Related data is tied on the same subregion of node.When power network object to be distributed in data grids, data are affine, and function can
With by object storage key (key) association by the same subregion of one group of relevant object binding to certain node, to realize meter
The efficient splicing for the evidence that counts.Subregion consciousness (Partition Awareness) function of memory data grid can guarantee simultaneously
Calculating relevant to this group of data executes on this node, farthest to reduce the Data Migration in calculating process.For example,
It can guarantee that all objects relevant to certain Load flow calculation case are stored in calculating using the affine function of data in Load flow calculation
In the same subregion of node, while it can guarantee that Load flow calculation algorithm executes on this partitioned nodes using subregion consciousness function.
Each element object of one power network object is carried out serializing and forms a large amount of key-value pair by wrapper, and according to member
Part type is classified, and is stored in a series of container IMap as provided by memory data grid, and the affine function of data is
It is to be managed to the district location of key-value pair physical holding of the stock.Make data according to distribution needed for calculating using the affine function of data
In data grids, then wrapper can be efficiently a large amount of whenever needing complete power network object to carry out simulation calculation
Key-value pair carry out unserializing and organizing to form power network object again.
The realization for function that data are affine is realized by key-value pair " key ".Such as Figure 10, electric network model is stored in a system
It arranges in IMap container, but Net IMap container and component container (Bus IMap, Branch IMap etc.) are different: in figure
The key-value pair saved in Net IMap is with " netKey " for key, and netKey is long long in Java, such as 1010000；And
For the key-value pair of Bus IMap and Branch IMap using ElementKey as key, ElementKey is that number is realized in the present embodiment design
According to the java class of affine functional interface PartitionAware, while realizing that it binds sectoring function getPartitionKey ()
With setting key value to the district location of binding.Based on this function, when key-value pair uses ElementKey class as key, only need
The binding Labelling Regions unification for setting ElementKey object is associated with netKey, then all key-value pairs will be affine by data
Function binding is in same subregion.
For ElementKey class as shown in Figure 10 lead frame, different ElemetKey object properties elementId is unique
, it is to discriminate between the coding of different elements, and by setting Labelling Regions attribute netKey (1010000), with Net object institute
The key netKey of the key-value pair (netKey, value) of formation is consistent, and can be realized that so-called " data are according to needed for calculating
Be distributed in data grids " data distribution strategy, then there is no need to evidence of fetching in other calculate nodes in calculating process,
To realize the efficient splicing for calculating data, guarantee the application efficiency of memory data grid.
Wrapper is handled " key " of key-value pair during being serialized: when each element sequences
After forming value, distribute one unique (attribute elementId is different) and bind subregion association (attribute netKey is identical)
ElementKey object, to realize that data are affine.
4, electrical network analysis memory computing architecture
Electrical network analysis memory computing architecture is as shown in figure 11.With the Power Network Modeling Method and memory data grid of object-oriented
Based on technology, the power system simulation model based on distributed memory data grids is generated.It, will using service-oriented programming idea
The simulation algorithm of User Exploitation is encapsulated on grid simulation object model with service form.When external request accesses data or processing
These can be executed when data and data are stored in the simulation algorithm of the same position to provide efficient calculate and service.
Electrical network analysis memory computing technique provided in this embodiment is packaged in the form of calculating service.The external world is to calculate clothes
Business API Calls mode executes electrical network analysis calculating process in memory data grid.User can also pass through memory computing architecture
The interface of offer sends computation requests to data grids, and respective algorithms is called to carry out grid simulation calculating in calculate node, and
Calculated result is returned into application.Relevant emulation data can efficiently be organized by " key " in calculate node and passed through anti-
Serializing forms power system simulation model object, then carries out data processing and executes analytical calculation process.
The key point of the present embodiment is that big data processing generallys use the distributed treatment based on computer cluster.Figure
12 be the typically distributed data processing solution based on data/address bus.Data are stored on back end, when calculating
Data are sent in calculate node by data/address bus from back end, this is the distributed data of one typical " data are mobile "
Handle design method.In Figure 13, memory data grid is made of computer cluster.Data are stored in the section of memory data grid
It in point memory, sends computation requests on the node of storing data according to calculating demand and carries out data processing, " moved to realize
Move algorithm rather than mobile data " data processing mode, utmostly to reduce data transmission and magnetic disc i/o operation, raising is always
Body computational efficiency, here it is the core concepts that memory calculates.
In grid simulation analysis, electric network model and calculating data will finally be loaded onto calculator memory and calculate
Analysis, thus power grid calculator memory implementation model is one of power network modeling research critical issue.And big data analysis is usually
It is parallel in a distributed computing environment to carry out, it is therefore necessary to research grid simulation point in multi -CPU/Core distributed computing environment
Analyse memory object modeling problem.The present embodiment is for the performance bottle for carrying out electrical network analysis in large-scale computer cluster environment
Neck, the memory computing technique suitable for electrical network analysis of proposition are in the structure (memory calculating) and internal storage data model of program
Based on multi -CPU/Core distributed computing environment design, there is (the computer under multicomputer node environment
Cluster) distributed variable-frequencypump function.
The electrical network analysis memory computing technique that the present embodiment proposes stores electrical network analysis in distributed memory data grids
Data model.Using micro services (Micro-Service) framework and service-oriented programming idea, by grid simulation algorithm to take
Business form is packaged in electrical network analysis model, and electric network model is allowed to provide efficient electrical network analysis in a distributed computing environment
Calculate service.The high efficiency for calculating service is to calculate calculation by the way that electric network model is placed on calculate node (subregion) neutralization analysis
Method executes in same calculate node, model and algorithm information are directly realized by memory exchange.Memory data grid
Function that data are affine is to guarantee that the model object collection for emulating case is stored in the same data grids subregion；Internal storage data net
The subregion consciousness function of lattice guarantees that calculating relevant to this group of data executes on this node, so that electric network model in simulation process
Internal information exchange needs not move through network communication.
The technical solution of the embodiment of the present invention changes the design in traditional grid simulation software design centered on algorithm
Mode provides a kind of data-centered simulation calculation mould for calculating mode based on memory for grid simulation software design
Formula.By this calculating mode, data persistently save and can realize model real-time update and in memory based on historical data
Search matching primitives.This technology uses the Distribution Strategy of " data are according to needed for calculating " in distributed environment, simultaneously number
According to stream without disk, evades to greatest extent implement electric system simulation in large-scale computer cluster environment in design
Efficiency bottle neck --- disk and network data I/O.In addition to this, this technology also supports flexible, efficient data interaction, in reality
When system in it is more advantageous compared to tradition data model file-based.It is to solve distributed (or cloud) meter that memory, which calculates core,
Calculate data migration problems in environment.Memory calculates in terms of grid simulation parser implementation and traditional grid simulation analysis is soft
Part is without too big difference.
Therefore, on the whole, the scheme of the present embodiment is namely based on Figure 14, collects power grid number by remote terminal (RTU)
According to rear, distributed data base solution is obtained using Data Grid Technology.Wherein, the modeling pattern of electric network model use towards
Before the method for object modeling, power network object model and memory data grid Integrated Solution and specific implementation can refer to the present embodiment
The power system simulation model technology in the memory data grid mentioned is stated, during realization, key problem in technology point is then previously mentioned
Data affine technolog, the final whole framework for realizing memory calculating.
Embodiment three:
Referring to Fig.1 5, the memory computing system suitable for electrical network analysis, comprising:
Acquisition unit 10, for acquiring electric network data；
First modeling unit 20, for establishing the first power network object model towards power network object according to electric network data；
Second modeling unit 30, for being established based on memory using power network object model and memory data grid integrated approach
Second power network object analysis model of data grids；
Data are affine unit 40, for binding electric network data using data affine technolog, to realize efficient access service；
Framework realizes unit 50, for integrally realizing the framework of electrical network analysis memory calculating using Enterprise SOA.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of memory calculation method suitable for electrical network analysis characterized by comprising
Acquire electric network data；
The first power network object model towards power network object is established according to the electric network data；
The second power grid of data grids based on memory is established using the power network object model and memory data grid integrated approach
Object analysis model；
According to the second power network object analysis model, the electric network data is bound using data affine technolog, it is efficient to realize
Access service；
The framework that electrical network analysis memory calculates integrally is realized using Enterprise SOA.
2. the memory calculation method according to claim 1 suitable for electrical network analysis, which is characterized in that described according to
Electric network data establishes the first power network object model towards power network object
Power grid admittance matrix is generated according to the electric network data；
The first power network object model towards bus and branch is generated according to the power grid admittance matrix, wherein described the
One power network object model is the network topology structure for directly storing simulation parameter.
3. the memory calculation method according to claim 1 suitable for electrical network analysis, which is characterized in that described in the use
Power network object model and memory data grid integrated approach establish the second power network object analysis model of data grids based on memory
Include:
Using unicomputer power network object modeling method and open source memory data grid technology, by the power network object model and institute
Memory data grid is stated to carry out integrating the second power network object analysis model.
4. the memory calculation method according to claim 3 suitable for electrical network analysis, which is characterized in that first power grid
Object model includes power network object and element object, described to collect the power network object model and the memory data grid
Include: at the second power network object analysis model is obtained
The interface provided using the open source memory data grid technology, to each power network object and the element object into
Row serializing generates key, and is distributed and is stored into one or more buffer service nodes automatically according to the key, makes the power grid
Object and element object are corresponded by hash function and key, to establish the second power network object analysis model,
In, the power network object includes bus object, branch object, and the element object includes node object.
5. the memory calculation method according to claim 1 suitable for electrical network analysis, which is characterized in that the data are affine
Technology is that the power network object is distributed in memory data grid, has one group by key association the electricity of correlativity
On net object binding to the same subregion of node, and grid simulation algorithm is executed on the subregion.
6. the memory calculation method according to claim 5 suitable for electrical network analysis, which is characterized in that described to use data
Affine technolog binds the electric network data
After the power network object and element object serialize the key-value pair to be formed, by the power network object and the element object
Classification is stored in the memory data grid；
When needing the complete power network object to carry out simulation calculation, the key-value pair is subjected to unserializing, is reorganized
Form the power network object；
On the same subregion, the grid simulation algorithm is executed to the power network object.
7. the memory calculation method according to claim 1 suitable for electrical network analysis, which is characterized in that the electrical network analysis
The framework that memory calculates is encapsulated into simulation algorithm in the form of services on the electrical network analysis model, when external request accesses
When data or processing data, then executes and be stored in the simulation algorithm of the same position with the data to provide and calculate clothes
Business.
8. the memory calculation method according to claim 4 suitable for electrical network analysis, which is characterized in that described to each institute
State power network object and the element object carry out serializing and generate key include:
The power network object and the element object are subjected to serializing using power network object model wrapper and are converted into binary system
Form is pushed in the memory data grid in the form of key-value pair.
9. the memory calculation method according to claim 6 suitable for electrical network analysis, which is characterized in that described by the key
Value forms the power network object and includes: to unserializing, reorganization is carried out
Using power network object model wrapper, unserializing is carried out to each key-value pair by functional expression interface, forms institute
State power network object.
10. a kind of memory computing system suitable for electrical network analysis characterized by comprising
Acquisition unit, for acquiring electric network data；
First modeling unit, for establishing the first power network object model towards power network object according to the electric network data；
Second modeling unit, for being counted based on memory using the power network object model and the foundation of memory data grid integrated approach
According to the second power network object analysis model of grid；
Data are affine unit, for binding the electric network data using data affine technolog, to realize efficient access service；
Framework realizes unit, for integrally realizing the framework of electrical network analysis memory calculating using Enterprise SOA.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810777084.8A CN109063980A (en) | 2018-07-16 | 2018-07-16 | Memory calculation method and system suitable for electrical network analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810777084.8A CN109063980A (en) | 2018-07-16 | 2018-07-16 | Memory calculation method and system suitable for electrical network analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063980A true CN109063980A (en) | 2018-12-21 |
Family
ID=64816673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810777084.8A Pending CN109063980A (en) | 2018-07-16 | 2018-07-16 | Memory calculation method and system suitable for electrical network analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063980A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241143A (en) * | 2020-01-09 | 2020-06-05 | 湖南华博信息技术有限公司 | Distributed calculation method and system for water supply amount and water fee |
| CN111262838A (en) * | 2020-01-09 | 2020-06-09 | 南方电网科学研究院有限责任公司 | Intelligent analysis method, system and equipment for network security |
| CN112751334A (en) * | 2020-12-21 | 2021-05-04 | 中国电力科学研究院有限公司 | Power grid online modeling method and system based on memory computing architecture |
| CN113484684A (en) * | 2021-07-16 | 2021-10-08 | 国网辽宁省电力有限公司 | Power distribution network multiple fault diagnosis system and method under non-sound fault information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104599032A (en) * | 2014-11-28 | 2015-05-06 | 国家电网公司 | Distributed memory power grid construction method and system for resource management |
| CN105405070A (en) * | 2015-12-03 | 2016-03-16 | 国家电网公司 | Distributed memory power grid system construction method |
| US20160141177A1 (en) * | 2013-06-25 | 2016-05-19 | Jürgen Steiger | Formulations for producing indium oxide-containing layers, process for producing them and their use |
-
2018
- 2018-07-16 CN CN201810777084.8A patent/CN109063980A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160141177A1 (en) * | 2013-06-25 | 2016-05-19 | Jürgen Steiger | Formulations for producing indium oxide-containing layers, process for producing them and their use |
| CN104599032A (en) * | 2014-11-28 | 2015-05-06 | 国家电网公司 | Distributed memory power grid construction method and system for resource management |
| CN105405070A (en) * | 2015-12-03 | 2016-03-16 | 国家电网公司 | Distributed memory power grid system construction method |
Non-Patent Citations (1)
| Title |
|---|
| 冯东豪: "支持快速在线分析的电网实时数据建模技术", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241143A (en) * | 2020-01-09 | 2020-06-05 | 湖南华博信息技术有限公司 | Distributed calculation method and system for water supply amount and water fee |
| CN111262838A (en) * | 2020-01-09 | 2020-06-09 | 南方电网科学研究院有限责任公司 | Intelligent analysis method, system and equipment for network security |
| CN112751334A (en) * | 2020-12-21 | 2021-05-04 | 中国电力科学研究院有限公司 | Power grid online modeling method and system based on memory computing architecture |
| CN113484684A (en) * | 2021-07-16 | 2021-10-08 | 国网辽宁省电力有限公司 | Power distribution network multiple fault diagnosis system and method under non-sound fault information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063980A (en) | Memory calculation method and system suitable for electrical network analysis | |
| Daki et al. | Big Data management in smart grid: concepts, requirements and implementation | |
| Alresheedi et al. | Improved multiobjective salp swarm optimization for virtual machine placement in cloud computing | |
| Liu et al. | A survey on workflow management and scheduling in cloud computing | |
| CN106326331A (en) | Intelligent power utilization data service system based on cloud computation | |
| CN108932588B (en) | Hydropower station group optimal scheduling system with separated front end and rear end and method | |
| WO2017167095A1 (en) | Model training method and device | |
| CN105049218A (en) | PhiCloud cloud charging method and system | |
| CN111241301A (en) | Knowledge graph representation learning-oriented distributed framework construction method | |
| Liu et al. | Graph computation and its applications in smart grid | |
| CN115954933A (en) | Power grid digital twin system construction method and device, electronic equipment and storage medium | |
| CN106921702A (en) | It is a kind of based on service-oriented power distribution network information physical system | |
| CN105930417A (en) | Big data ETL (Extract-Transform-Load) interactive processing platform based on cloud computing | |
| CN103473247B (en) | Geological data information cluster mechanism and interface aggregation system | |
| CN104407811B (en) | A kind of merging I/O device based on cloud computing | |
| CN104299170B (en) | Intermittent energy source mass data processing method | |
| Kim et al. | Development of the big data management system on national virtual power plant | |
| Smidt et al. | Smart application development for IoT asset management using graph database modeling and high-availability web services | |
| Ni et al. | An ant colony optimization for the composite SaaS placement problem in the cloud | |
| Mubarak et al. | A parallel ghosting algorithm for the flexible distributed mesh database | |
| CN114693262A (en) | Smart city information grid operating system | |
| CN103442088B (en) | A kind of cloud computing system of dividing into groups to calculate | |
| CN108573360A (en) | The global analysis of adaptation power grid active schedule demand and preventing control method and system | |
| Cheng et al. | [Retracted] Efficient Management and Application of Human Resources Based on Genetic Ant Colony Algorithm | |
| CN114764389A (en) | Heterogeneous simulation test platform of joint learning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |