CN112444851A - Reverse time migration imaging method based on MapReduce parallel framework and storage medium - Google Patents
Reverse time migration imaging method based on MapReduce parallel framework and storage medium Download PDFInfo
- Publication number
- CN112444851A CN112444851A CN201910817050.1A CN201910817050A CN112444851A CN 112444851 A CN112444851 A CN 112444851A CN 201910817050 A CN201910817050 A CN 201910817050A CN 112444851 A CN112444851 A CN 112444851A
- Authority
- CN
- China
- Prior art keywords
- job
- data
- tasks
- map
- parallel framework
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 56
- 230000005012 migration Effects 0.000 title claims abstract description 56
- 238000003384 imaging method Methods 0.000 title claims abstract description 31
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000007726 management method Methods 0.000 claims abstract description 13
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000013500 data storage Methods 0.000 claims 1
- 238000013523 data management Methods 0.000 abstract description 4
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 238000009745 resin transfer moulding Methods 0.000 description 1
- 238000001721 transfer moulding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/34—Displaying seismic recordings or visualisation of seismic data or attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/70—Other details related to processing
- G01V2210/74—Visualisation of seismic data
Abstract
The application provides a reverse time migration imaging method and a storage medium based on a MapReduce parallel framework, wherein the method comprises the following steps: determining the total number of operation tasks aiming at the pre-stack seismic data volume; in the Map stage, performing Map internal shot domain migration and memory superposition on all job tasks in each Map job on each node of at least one node; outputting the memory superposed data volume in blocks; in the Reduce stage, the output migration results are parallelly superposed in real time to obtain the migration results of the total number of the operation tasks; and merging the deviation results of the total number of the job tasks and outputting a final result. By the method and the storage medium, the existing parallel framework can be optimized, the IO performance of data management is improved based on a distributed file system, RTM operation efficiency is improved, dynamic management of RTM operation is realized based on YARN operation management, an operation protection mechanism of single-node task failure is provided, and operation fault tolerance is improved.
Description
Technical Field
The invention relates to the technical field of geophysical exploration, in particular to an RTM imaging technology and a storage medium based on a MapReduce parallel framework, forms a reverse time migration imaging algorithm based on the MapReduce parallel framework, and can be applied to a reverse time migration technology in petroleum geophysical exploration.
Background
The reverse time migration technology is the most perfect seismic imaging technology of the current theoretical method, is used as a pre-stack, depth domain and two-way wave equation migration method, has the advantages of few assumed conditions, high precision, adaptability to any complex medium, no dip angle limitation and amplitude preservation, and can carry out high-precision imaging on underground fine and complex structures. However, since 1978, the popularization of large-scale production and application is low, and the main reason for restricting the development is that the reverse time migration technology itself needs huge storage and calculation amount.
In recent years, with the continuous development of computer technology, people have been dedicated to improving the calculation efficiency of Reverse Time Migration (RTM), and the main ideas are focused on two aspects: 1 optimization of the algorithm itself 2. acceleration is achieved by means of a high performance computing platform. At present, an MPI parallel framework and CPU/GPU cooperative acceleration based scheme is mainly adopted by RTM technology put into production on the market, and based on the scheme, RTM efficiency is improved to a great extent. However, MPI is a programming model based on message passing, nodes of an algorithm based on an MPI parallel framework need to communicate with each other, and as the data volume becomes larger, a large amount of time is spent on the data communication among processes, so that the high-efficiency operation of the algorithm communication is ensured, and high requirements are imposed on the stability of a cluster and the parallel complexity of the algorithm. In addition, due to the communication reason, the entire operation is interrupted when one process is interrupted in the operation based on the MPI, the fault tolerance capability is poor, and although the current operation has the breakpoint protection function, the real-time dynamic management of the operation is difficult to achieve by manually retransmitting the operation, so that the time cost of the production operation is increased.
MapReduce is a programming mode based on a Hadoop distributed parallel framework, adopts Another Resource coordinator (Yet other Resource coordinator, namely 'YARN', namely a job scheduling manager), can perform job management on a certain single process, has good fault-tolerant and load balancing capabilities, and improves the IO performance of data by a unique distributed data management mode. The MapReduce calculation model is higher in grade and low in development difficulty, developers mainly pay attention to Map and Reduce operations, and programming complexity is reduced.
Aiming at the problems, considering that real-time communication is not needed between parallel node operations of the RTM technology, a reverse time migration imaging technology based on a MapReduce parallel framework needs to be developed, RTM operation efficiency is improved, and operation dynamic management is realized.
Disclosure of Invention
The embodiment of the invention provides a reverse time migration imaging technology based on a MapReduce parallel framework, which can improve the calculation efficiency and large-scale data adaptability of RTM (resin transfer molding), can realize dynamic management of operation to keep load balance of the operation, and provides efficient and accurate seismic imaging data for seismic exploration.
In a first aspect, the invention provides a reverse time migration imaging method based on a MapReduce parallel framework, which comprises the following steps: determining the total number of operation tasks aiming at the pre-stack seismic data volume; in the Map stage, performing Map internal shot domain migration and memory superposition on all job tasks in each Map job on each node of at least one node; outputting the memory superposed data volume in blocks; in the Reduce stage, the output migration results are parallelly superposed in real time to obtain the migration results of all the job tasks; and merging the offset results of all the job tasks and outputting a final result.
In one possible implementation manner of the first aspect, the total number of job tasks is determined by: sorting the pre-stack seismic data volume into common shot gather data; and aiming at the common shot gather data, determining the total number of the operation tasks according to a preset first data unit block size, wherein the first data unit block size can be dynamically adjusted according to computing resources.
In a possible implementation manner of the first aspect, the outputting the memory stack data volume in blocks includes: and partitioning the memory stacked data body according to the block size of a second data unit and outputting the partitioned data body, wherein the block size of the second data unit is 512M.
In a possible implementation manner of the first aspect, the performing parallel superposition on the output migration results in real time to obtain the migration results of all the job tasks includes: and starting threads with corresponding number to perform real-time parallel superposition on the results output by each Map at the same position according to the number of the partitioned migration result blocks.
In one possible implementation manner of the first aspect, the first data unit block size is 512M, 1G, or 2G.
In a possible implementation manner of the first aspect, the total number of the job tasks and the number of the nodes have the same magnitude, so as to ensure the parallelism of the job and avoid that redundant computation affects the operation efficiency of the job due to excessive total tasks.
In a possible implementation manner of the first aspect, the MapReduce parallel framework includes a big data distributed file system, so as to implement storage of big data and improve IO performance.
In a possible implementation manner of the first aspect, the MapReduce parallel framework uses a job scheduling manager to implement dynamic management of jobs, so that load balancing of jobs is ensured.
In a second aspect, the invention also provides a computer readable storage medium storing computer code configured to, when executed by a processor, perform the steps of the method of the first aspect and embodiments thereof.
Based on the technical scheme, the MapReduce parallel framework-based reverse time migration imaging method disclosed by the embodiment of the invention can reduce the programming complexity and improve the RTM operation efficiency by using the MapReduce parallel framework to realize a reverse time migration technology, and the MapReduce parallel framework adopts a YARN operation scheduling manager to manage the operation of a certain single process, so that the method has good fault-tolerant and load balancing capabilities, and the unique distributed data management mode also improves the IO performance of data.
The features mentioned above can be combined in various suitable ways or replaced by equivalent features as long as the object of the invention is achieved.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings. Wherein:
FIG. 1 is a schematic diagram of an implementation of an RTM parallel algorithm based on an MPI parallel framework;
FIG. 2 is a flowchart of an implementation of an RTM parallel algorithm based on a MapReduce parallel framework according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a MapReduce parallel framework-based RTM imaging method according to an embodiment of the present invention;
FIG. 4 is a migration result of one of the lines of a seismic data based on MPI parallel framework and MapReduce parallel framework.
In the drawings, like parts are provided with like reference numerals. The drawings are not to scale.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Fig. 1 shows a schematic diagram of an RTM parallel algorithm implementation based on an MPI parallel framework, and as shown in fig. 1, an RTM parallel algorithm implementation based on an MPI parallel framework includes: a prestack data volume; master node Master 0, Master 1; n computing nodes; and finally, shifting the result.
Specifically, as shown in fig. 1, the implementation of the RTM parallel algorithm based on the MPI parallel framework includes: a prestack data volume which is an input seismic data volume; the Master node Master 0 traverses and segments the input seismic data volume according to the total shot number and the currently given number N of the computing nodes, so as to establish a database and determine tasks allocated to each computing node, and before operation, the Master node Master 0 firstly allocates the tasks processed by each node through message transmission; the N computing nodes carry out parallel data migration according to the instruction of the Master node Master 0 and send migration results to the next stage for execution when the single shot is completed; the Master node Master 1 is used for superposing the offset data transmitted by the N computing nodes; and a final offset result, which is an output result of the Master node Master 1 superimposing the offset data.
As can be seen from the flowchart of fig. 1 showing the RTM parallel algorithm based on the MPI parallel framework, nodes based on the MPI parallel framework algorithm need to communicate with each other, and in the operation based on the MPI, when one process is interrupted, the whole operation is interrupted, the fault tolerance capability and the load balancing capability of the framework are poor, and although the current operation has the breakpoint protection function, it is difficult to perform real-time dynamic management of the operation by manual retransmission, so that the time cost and the labor cost of the production operation are increased.
Fig. 2 and fig. 3 are flowcharts of an implementation of an RTM parallel algorithm based on a MapReduce parallel framework according to an embodiment of the present invention. As shown in fig. 2, the RTM parallel algorithm based on MapReduce parallel framework is implemented by: a pre-stack seismic data volume; defining a data block and dividing a task; a MAP stage; a Reduce stage; and finally, shifting the result.
Specifically, as shown in fig. 3, the realization of the RTM imaging method 100 based on the MapReduce parallel framework according to the embodiment of the present invention includes:
s110, aiming at the pre-stack seismic data volume, determining the total number of operation tasks;
s120, in the Map stage, performing Map internal shot domain migration and memory superposition on all the job tasks in each Map job on each node of at least one node;
s130, outputting the memory stacked data volume in blocks;
s140, in the Reduce stage, the output migration results are parallelly superposed in real time to obtain the migration results of the total number of the operation tasks; and
and S150, merging the deviation results of the total number of the operation tasks and outputting a final result.
Herein, the prestack data volume refers to an input seismic data volume; the total number of job tasks may be determined by the following steps:
the prestack seismic data are sorted into shot-shared gather data, based on the size (set as M) of input data and existing computing resources (such as the number of nodes is N), according to the task allocation principle of MapReduce, a user parameter (namely the size of a first data unit block) is given, the user parameter is used for setting the task quantity of a single Map, namely the task quantity is controlled according to the data slice size M (512M, 1G or 2G) of the data block, the actual operation task number N is set as M/M, the task book is controlled on the magnitude of the existing computing resources N, the operation task number can be reasonably controlled, and Hadoop can automatically perform task allocation based on YARN operation management to achieve optimal load balance among the nodes.
In S120, the MAP phases refer to MAP in-shot domain migration and superposition. Specifically, the Map stage currently performs reverse time migration imaging in N maps, i.e., performs parallel RTM migration on input single shot gather data according to the task assigned to each compute node, thereby generating N migration results. Because the MapReduce parallel framework needs to write the imaging result onto the HDFS, and the IO of the data affects the efficiency of data superposition, the embodiment of the invention implements memory superposition on the imaging result of each gun in each MAP at the MAP stage.
And S130, outputting the imaging result after the current Map is finished, performing data segmentation on the output result according to the block size (512M per block) of the second data unit, setting the number of files output by each Map as n to perform data parallel superposition, and further improving the operation efficiency by reducing IO.
And in the step S140, namely, in the Reduce stage, the output migration results are superimposed in real time in parallel, so as to obtain the migration result of the total number of the job tasks. The Reduce stage is to superimpose the migration result in real time in parallel, and specifically, according to the number n of migration result blocks in the Map stage, n threads are started to superimpose block data at the same position output by the Map in parallel in real time.
Finally, in S160, the offset results of the total number of job tasks are merged and the final result is output. The final offset result refers to a final result of data merging and output, and specifically, a final complete offset data volume is output by performing protocol merging (protocol merging) on a result which is finally overlapped in the Reduce stage.
As can be seen from the flowchart for implementing the RTM parallel algorithm based on the MapReduce parallel framework shown in fig. 2, the MapReduce parallel framework is adopted in the embodiment of the present invention, so that the existing parallel framework is optimized and communication between nodes is avoided. Preferably, the user can control the total task number of the job in real time according to the size of the input data volume, so that the parallelism of the job is ensured, and the problem that the running efficiency of the job is influenced by redundant calculation due to excessive total tasks is avoided. Further, the embodiment of the invention improves the efficiency of overlaying the imaging results by performing data segmentation (each block is 512M in size) on each Map imaging offset result and then overlaying the results in parallel, so as to reduce data IO and further improve the operation efficiency. In addition, the embodiment of the invention improves the IO performance of data management based on a distributed file system, realizes the improvement of RTM operation efficiency, realizes the dynamic management of RTM operation based on YARN operation management, has an operation protection mechanism of single-node task failure, and improves the fault tolerance of operation.
In an exemplary embodiment of the invention, FIG. 4 shows the migration results for one of the lines of a seismic data based on MPI parallel framework (a) and MapReduce parallel framework (b). Specifically, the RTM algorithm based on MapReduce is deployed in a Hadoop running environment of a 50GPU node cluster. And respectively carrying out actual data test on RTMs under the MPI framework and the MapReduce framework under the same hardware environment, wherein the actual data is pre-stack shot gather data with the size of 2.4T 24279 shots, and the size of the migration result generated by the two implementation modes is 10.3G. From the operation results shown in fig. 4, it can be seen that: the RTM technology based on MapReduce and the RTM calculation result based on MPI are kept consistent, in addition, the operation overall performance of the RTM technology based on MapReduce provided by the invention can be improved through operation running state analysis, the calculation efficiency is improved by 15 percent compared with that of MPI, and the higher fault tolerance of the dynamic operation management of MapReduce is proved through testing single-process operation.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Additionally, the present application, in further embodiments, also provides a computer readable storage medium storing computer code configured to, when executed by a processor, perform the steps of the method described above.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that features described in different dependent claims and herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (10)
1. A reverse time migration imaging method based on a MapReduce parallel framework is characterized by comprising the following steps:
determining the total number of operation tasks aiming at the pre-stack seismic data volume;
in the Map stage, performing Map internal shot domain migration and memory superposition on all job tasks in each Map job on each node of at least one node to obtain a memory superposition data volume;
outputting the memory stacked data volume in blocks;
in the Reduce stage, the output migration results are parallelly superposed in real time to obtain the migration results of all the job tasks; and
and merging the offset results of all the job tasks and outputting a final result.
2. The MapReduce parallel framework-based reverse time migration imaging method according to claim 1, wherein the total number of job tasks is determined by:
sorting the pre-stack seismic data volume into common shot gather data;
and determining the total number of the operation tasks according to a preset first data unit block size aiming at the common shot gather data, wherein the data unit block size can be dynamically adjusted according to the number of nodes.
3. The MapReduce parallel framework-based reverse time migration imaging method as claimed in claim 2, wherein the performing the offset of the intra-Map shot domain and the memory stacking and block outputting of all job tasks in each Map job on each node of at least one node comprises:
performing reverse time migration imaging on each input single shot gather data in each Map operation;
and performing memory superposition on the reverse time migration imaging result of each single shot gather data in the Map to obtain a memory superposition data volume.
4. The MapReduce parallel framework-based reverse time migration imaging method as set forth in claim 3, wherein the outputting of the memory stack data volume in blocks comprises:
and partitioning the memory stacked data body according to the block size of a second data unit and outputting the partitioned data body, wherein the block size of the second data unit is 512M.
5. The MapReduce parallel framework-based reverse time migration imaging method as claimed in claim 4, wherein the parallel superposition of the output migration results in real time to obtain the migration results of all job tasks comprises:
and starting threads with corresponding number to perform real-time parallel superposition on the results output by each Map at the same position according to the number of the partitioned migration result blocks.
6. The MapReduce parallel framework-based reverse time migration imaging method according to any one of claims 2 to 5, wherein the first data unit block size is 512M, 1G or 2G.
7. The MapReduce parallel framework-based reverse time migration imaging method according to any one of claims 2 to 5, wherein the total number of the job tasks is in the same order of magnitude as the number of nodes, so as to ensure the parallelism of the job and avoid redundant computation from affecting the operation efficiency of the job due to excessive total tasks.
8. The MapReduce parallel framework-based reverse time migration imaging method as claimed in any one of claims 1 to 5, wherein the MapReduce parallel framework comprises a big data distributed file system to realize big data storage and improve IO performance.
9. The MapReduce parallel framework-based reverse time migration imaging method as claimed in any one of claims 1 to 5, wherein the MapReduce parallel framework utilizes a job scheduling manager to realize dynamic management of jobs and ensure load balancing of jobs.
10. A computer readable storage medium, characterized in that it stores computer code configured to perform the steps of the method of any of claims 1 to 9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910817050.1A CN112444851A (en) | 2019-08-30 | 2019-08-30 | Reverse time migration imaging method based on MapReduce parallel framework and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910817050.1A CN112444851A (en) | 2019-08-30 | 2019-08-30 | Reverse time migration imaging method based on MapReduce parallel framework and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112444851A true CN112444851A (en) | 2021-03-05 |
Family
ID=74735265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910817050.1A Pending CN112444851A (en) | 2019-08-30 | 2019-08-30 | Reverse time migration imaging method based on MapReduce parallel framework and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112444851A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120110047A1 (en) * | 2010-11-15 | 2012-05-03 | International Business Machines Corporation | Reducing the Response Time of Flexible Highly Data Parallel Tasks |
| CN102662639A (en) * | 2012-04-10 | 2012-09-12 | 南京航空航天大学 | Mapreduce-based multi-GPU (Graphic Processing Unit) cooperative computing method |
| CN104570081A (en) * | 2013-10-29 | 2015-04-29 | 中国石油化工股份有限公司 | Pre-stack reverse time migration seismic data processing method and system by integral method |
| JP2015095096A (en) * | 2013-11-12 | 2015-05-18 | 株式会社日立製作所 | Mapreduce job execution system and mapreduce job execution method |
| CN105445792A (en) * | 2015-11-26 | 2016-03-30 | 中国科学院地质与地球物理研究所 | Pre-stack multiple reverse time migration earthquake data processing method and system |
| US20180288154A1 (en) * | 2017-04-02 | 2018-10-04 | Sas Institute Inc. | Techniques for Reading From and Writing to Distributed Data Stores |
| CN109657197A (en) * | 2017-10-10 | 2019-04-19 | 中国石油化工股份有限公司 | A kind of pre-stack depth migration calculation method and system |
-
2019
- 2019-08-30 CN CN201910817050.1A patent/CN112444851A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120110047A1 (en) * | 2010-11-15 | 2012-05-03 | International Business Machines Corporation | Reducing the Response Time of Flexible Highly Data Parallel Tasks |
| CN102662639A (en) * | 2012-04-10 | 2012-09-12 | 南京航空航天大学 | Mapreduce-based multi-GPU (Graphic Processing Unit) cooperative computing method |
| CN104570081A (en) * | 2013-10-29 | 2015-04-29 | 中国石油化工股份有限公司 | Pre-stack reverse time migration seismic data processing method and system by integral method |
| JP2015095096A (en) * | 2013-11-12 | 2015-05-18 | 株式会社日立製作所 | Mapreduce job execution system and mapreduce job execution method |
| CN105445792A (en) * | 2015-11-26 | 2016-03-30 | 中国科学院地质与地球物理研究所 | Pre-stack multiple reverse time migration earthquake data processing method and system |
| US20180288154A1 (en) * | 2017-04-02 | 2018-10-04 | Sas Institute Inc. | Techniques for Reading From and Writing to Distributed Data Stores |
| CN109657197A (en) * | 2017-10-10 | 2019-04-19 | 中国石油化工股份有限公司 | A kind of pre-stack depth migration calculation method and system |
Non-Patent Citations (2)
| Title |
|---|
| 王庆喜 等: "云计算导论", 28 February 2018, 中国铁道出版社, pages: 75 * |
| 高新成: "基于云计算的逆时偏移数据处理方法研究", 中国博士学位论文全文数据库 工程科技I辑, no. 03, pages 38 - 73 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Adaptive asynchronous federated learning in resource-constrained edge computing | |
| CN104050042B (en) | The resource allocation methods and device of ETL operations | |
| CN105912399B (en) | Task processing method, device and system | |
| CN106843745A (en) | Capacity expansion method and device | |
| CN103793442B (en) | The processing method and system of spatial data | |
| US9563697B1 (en) | Calculating differences between datasets having differing numbers of partitions | |
| Teng et al. | Simmapreduce: A simulator for modeling mapreduce framework | |
| Song et al. | A load balancing scheme using federate migration based on virtual machines for cloud simulations | |
| CN104570081A (en) | Pre-stack reverse time migration seismic data processing method and system by integral method | |
| CN109344135A (en) | A kind of parallel seismic processing job scheduling method of the file lock of automatic load balancing | |
| CN105740085A (en) | Fault tolerance processing method and device | |
| CN100531070C (en) | Network resource scheduling simulation system | |
| Fang et al. | Integrating workload balancing and fault tolerance in distributed stream processing system | |
| CN109657197A (en) | A kind of pre-stack depth migration calculation method and system | |
| CN107301094A (en) | The dynamic self-adapting data model inquired about towards extensive dynamic transaction | |
| CN108932118B (en) | Card-based demand acquisition model establishing method | |
| Yang et al. | Formalizing mapreduce with csp | |
| CN112559525B (en) | Data checking system, method, device and server | |
| CN104360962B (en) | Be matched with multistage nested data transmission method and the system of high-performance computer structure | |
| CN112444851A (en) | Reverse time migration imaging method based on MapReduce parallel framework and storage medium | |
| Loring et al. | Improving performance of m-to-n processing and data redistribution in in transit analysis and visualization | |
| CN110110158A (en) | A kind of the memory space division methods and system of three-dimensional mesh data | |
| CN111025400A (en) | Hadoop-based seismic migration imaging operation endurance method and system | |
| US20210149746A1 (en) | Method, System, Computer Readable Medium, and Device for Scheduling Computational Operation Based on Graph Data | |
| CN110990059B (en) | Stream type calculation engine operation method and system for tilt data |
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 |