Airborne cloud computing control method and system in radiation environment, terminal and medium

Abstract

The application discloses an airborne cloud computing control method and system in a radiation environment, a terminal and a medium, relates to the technical field of cloud computing, and has the technical scheme as follows: receiving an application deployment service request sent by a service deployment party; establishing a service agent according to the application deployment service request, returning a service address to the service deployment party after a plurality of application program copies are generated by the service agent; after receiving a service execution request sent by the service deployment party, transmitting the application program copies to task machines arranged in different positions of an aircraft one by one; receiving copy return results output by the plurality of task machines after the plurality of task machines complete the calculation, determining a final return result according to the similarity of all the received copy return results, and transmitting the final return result to the service deployment party. The application performs redundant calculation on the same computing task through the position arrangement of physical devices and software implementation, schedules the computing task to different hardware for running, finally fuses the computing results, and gives reliable computing results.

Description

Technical Field

[0001] This invention relates to the field of cloud computing technology, and more specifically, to airborne cloud computing control methods, systems, terminals, and media in radiation environments. Background Technology

[0002] In the aerospace field, high-energy particle radiation is present in greater quantities and in greater intensity than in ordinary plains. High-energy particle radiation can cause "soft errors" in electronic components, also known as single-event upsets (SEUs). A "soft error" refers to an erroneous output signal from a memory or storage cell caused by radiation or an electromagnetic pulse, without causing permanent damage to the storage hardware. In more severe cases, the hardware will be permanently damaged, rendering subsequent computing and storage based on the damaged hardware unusable.

[0003] Soft errors occur when high-energy particles penetrate memory cells, causing changes in the stored state. In computer architecture, physical storage involves binary storage of 0s and 1s on memory cells. "Soft errors" cause abnormal changes to these 0s and 1s, such as 0 becoming 1 or 1 becoming 0, resulting in errors in the computer's stored content. When a computer performs tasks, all tasks rely on memory cells, where data is processed and calculated. When a "soft error" occurs, the data being calculated in the computer becomes incorrect, ultimately leading to functional abnormalities.

[0004] The aerospace field demands extremely high reliability of computational results. Current mainstream solutions employ radiation-resistant computing methods, but with relatively weak computational power. This is primarily because the higher the computational precision of a chip, the worse the radiation resistance of its internal components. When introducing new applications such as artificial intelligence into the aerospace field, these applications require massive computing resources, which existing low-performance chips cannot meet. Furthermore, due to the poor radiation resistance of high-performance computing equipment, relying solely on the hardware's inherent radiation resistance is insufficient to meet reliability requirements. Errors caused by high-energy particle radiation are difficult to detect, and these erroneous results can be applied to flight or other functions, potentially leading to catastrophic consequences. Therefore, researching and designing airborne cloud computing control methods, systems, terminals, and media for use in radiation environments is a pressing issue that requires our immediate attention. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this invention is to provide an airborne cloud computing control method, system, terminal, and medium under radiation conditions. In terms of physical equipment, the task machines for implementing cloud computing are deployed in different locations on the aircraft to reduce the possibility of simultaneous hardware interference. In terms of software implementation, the same computing task is redundantly computed and scheduled to run on different hardware. Finally, the computing results are fused to provide reliable computing results.

[0006] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0007] Firstly, an airborne cloud computing control method for use in a radiation environment is provided, including the following steps:

[0008] Receive application deployment service requests from the service deployment provider;

[0009] A service proxy is established based on the application deployment service request. After the service proxy generates multiple copies of the application, the service address is returned to the service deployer.

[0010] Upon receiving a service execution request from the service deployment party, the application copies are transmitted one by one to the mission machines distributed at different locations on the aircraft.

[0011] It receives the replica return results from multiple task machines after they have completed the calculation, determines the final return result based on the similarity of all received replica return results, and transmits the final return result to the service deployment party.

[0012] Furthermore, the service agent generates multiple application copies, fewer than the total number of idle task machines, based on the configuration requirements for CPU and memory utilization.

[0013] Furthermore, the number of application copies is an odd number greater than 3.

[0014] Furthermore, the application copy is deployed by selecting appropriate task machines after a comprehensive analysis of the task machine response rate and the degree of task machine distribution.

[0015] Furthermore, the application copies are randomly selected and placed on task machines in different locations.

[0016] Furthermore, the process for determining the final returned result is as follows:

[0017] Analyze the proportion of different results among the N replicas returned first, where N is a positive integer not less than half the number of application replicas, and take the replica return result corresponding to the largest proportion as the final return result;

[0018] Alternatively, when the number of identical copy results received reaches a set threshold, the corresponding identical copy result will be used as the final result.

[0019] Secondly, it provides an airborne cloud computing control system for radiation environments, including a cloud computing platform and multiple mission machines that are all connected to the cloud computing platform.

[0020] The cloud computing platform is used for:

[0021] Receive application deployment service requests from the service deployment provider;

[0022] A service proxy is established based on the application deployment service request. After the service proxy generates multiple copies of the application, the service address is returned to the service deployer.

[0023] Upon receiving a service execution request from the service deployment party, the application copies are transmitted one by one to the mission machines distributed at different locations on the aircraft.

[0024] In addition, it receives the replica return results from multiple task machines, determines the final return result based on the similarity of all received replica return results, and transmits the final return result to the service deployment party;

[0025] The task machine is used to perform calculations on the received application copy and output the copy return result.

[0026] Furthermore, the mission aircraft are distributed in a matrix arrangement at different positions on the aircraft in the horizontal plane.

[0027] Thirdly, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the airborne cloud computing control method in a radiation environment as described in any one of the first aspects.

[0028] Fourthly, a computer-readable medium is provided having a computer program stored thereon, the computer program being executed by a processor to implement the airborne cloud computing control method in a radiation environment as described in any one of the first aspects.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The airborne cloud computing control method under radiation environment proposed in this invention, on the physical equipment, arranges the task machines that realize cloud computing at different positions on the aircraft to reduce the impact of radiation environment on the results; on the software implementation, the same computing task is redundantly calculated and scheduled to run on different hardware, and finally the calculation results are fused to give reliable calculation results.

[0031] 2. This invention generates corresponding deployment strategies based on the task machine response rate and the degree of task machine dispersion, and calls up the corresponding task machines for calculation according to the deployment strategy, which can enhance the accuracy and reliability of the final returned results.

[0032] 3. This invention reduces the overall operating cycle of cloud computing by performing probability analysis on the results returned by selecting a portion of the replicas. Attached Figure Description

[0033] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0034] Figure 1 This is a flowchart from an embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram of the arrangement of the task machines in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0037] Example 1: Airborne cloud computing control method under radiation environment, such as Figure 1 As shown, it includes the following steps:

[0038] S1: Receives application deployment service requests from the service deployment provider;

[0039] S2: Establish a service proxy based on the application deployment service request. After the service proxy generates multiple copies of the application, it returns the service address to the service deployer.

[0040] S3: After receiving the service execution request from the service deployment party, transmit the application copies one by one to the mission machines distributed in different locations on the aircraft;

[0041] S4: Receive the replica return results output by multiple task machines after completing the calculation, determine the final return result based on the similarity of all received replica return results, and transmit the final return result to the service deployment party.

[0042] In terms of physical equipment, this invention deploys the cloud computing task machines at different locations on the aircraft to reduce the impact of the radiation environment on the results. In terms of software implementation, the same computing task is redundantly computed and scheduled to run on different hardware. Finally, the computing results are fused to provide reliable computing results.

[0043] Each task machine is equipped with basic CPU and ROM functions. The service agent generates multiple copies of the application, fewer than the total number of idle task machines, based on the configuration requirements of CPU and memory utilization.

[0044] To reduce the probability of having two or more final return results when merging replica return results, the number of application replicas should be an odd number greater than 3.

[0045] As an alternative implementation, the application copy is deployed by selecting appropriate task machines after a comprehensive analysis of the task machine response rate and the degree of task machine distribution.

[0046] For example, the process of deploying application copies on task machines is as follows: a distribution strategy is calculated with the first optimization objective being the maximum response rate of the task machines and the second optimization objective being the minimum distribution of task machines; and multiple application copies are deployed one by one on the corresponding idle task machines according to the distribution strategy.

[0047] For example, the process of deploying application copies on task machines is as follows: sort all idle task machines according to their response rate to obtain a first priority value for each task machine; sort all idle task machines according to their distribution to obtain a second priority value for each task machine; calculate the final priority value by weighting the first and second priority values, and select the task machines with the highest final priority values ​​to form a distributed deployment strategy; deploy multiple application copies one by one on the corresponding idle task machines according to the distributed deployment strategy.

[0048] It should be noted that the mission aircraft dispersion degree indicates the uniformity of the distribution of the selected mission aircraft throughout the entire aircraft deployment area. For example, the ratio of the total aircraft deployment area to the number of selected mission aircraft can be used as the coverage area of ​​a single mission aircraft, and the degree of overlap of all coverage area circles can be used to represent the mission aircraft dispersion degree. In addition, the mission aircraft dispersion degree can also be calculated using methods such as standard deviation and variance.

[0049] As an alternative implementation, application copies can be randomly distributed across different task machines.

[0050] This invention reduces the overall runtime of the cloud computing process by performing probability analysis on the results returned from a subset of replicas.

[0051] As an optional implementation, the proportion of different results among the first N received replica return results is analyzed, where N is a positive integer not less than half the number of application replicas, and the replica return result corresponding to the largest proportion is taken as the final return result;

[0052] As another optional implementation, when the number of identical copy return results received reaches a set threshold, the corresponding identical copy return result is used as the final return result.

[0053] Example 2: Airborne cloud computing control system in a radiation environment, such as Figure 2 As shown, it includes a cloud computing platform and multiple task machines that are all connected to the cloud computing platform.

[0054] The cloud computing platform is used for: receiving application deployment service requests from the service deployment party; establishing a service proxy based on the application deployment service request, generating multiple application copies through the service proxy, and returning the service address to the service deployment party; receiving service execution requests from the service deployment party, transmitting the application copies one by one to the mission machines distributed at different locations on the aircraft; and receiving the copy return results from multiple mission machines, determining the final return result based on the similarity of all received copy return results, and transmitting the final return result to the service deployment party. The mission machines are used to perform calculations on the received application copies and output the copy return results.

[0055] The mission aircraft are distributed in a matrix arrangement in the horizontal plane at different positions of the aircraft, and different mission aircraft operate independently. Mission aircraft a and mission aircraft b can be the same or different mission aircraft.

[0056] Working principle: In terms of physical equipment, this invention deploys the cloud computing task machines at different locations on the aircraft to reduce the impact of the radiation environment on the results; in terms of software implementation, the same computing task is redundantly computed and scheduled to run on different hardware, and finally the computing results are fused to provide reliable computing results.

[0057] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An airborne cloud computing control method under radiation environment, characterized by: Includes the following steps: Receive application deployment service requests from the service deployment provider; A service proxy is established based on the application deployment service request. After generating multiple application copies, the service proxy returns the service address to the service deployer. The service proxy generates multiple application copies in a number less than the total number of idle task machines, based on the configuration requirements of CPU and memory utilization. The number of application copies is an odd number greater than 3. Upon receiving a service execution request from the service deployment provider, application copies are transmitted one by one to mission machines distributed across different locations on the aircraft. The application copies are then deployed to appropriate mission machines based on a comprehensive analysis of mission machine response rates and distribution levels. Specifically, the process of deploying application copies to mission machines involves: calculating a distribution strategy with the maximum mission machine response rate as the first optimization objective and the minimum mission machine distribution level as the second optimization objective; and deploying multiple application copies one by one to corresponding idle mission machines according to the distribution strategy. Furthermore, all idle mission machines are sorted according to their response rates to obtain the order of priority for different mission machines. First, a priority value is assigned. All idle mission machines are sorted according to their dispersion, resulting in a second priority value for each mission machine. A final priority value is calculated based on the weights of the first and second priority values, and the mission machines ranked highest by the final priority value are selected to form a distributed deployment strategy. Multiple application copies are then deployed one by one to the corresponding idle mission machines according to the distributed deployment strategy. The dispersion of mission machines represents the uniformity of the selected mission machines' distribution throughout the entire aircraft deployment area. The ratio of the total aircraft deployment area to the number of selected mission machines is used as the coverage area of ​​a single mission machine, and the degree of overlap of all coverage areas represents the dispersion of mission machines. It receives the replica return results from multiple task machines after they have completed the calculation, determines the final return result based on the similarity of all received replica return results, and transmits the final return result to the service deployment party.

2. The airborne cloud computing control method under radiation environment according to claim 1, characterized in that, The process for determining the final returned result is as follows: Analyze the proportion of different results among the N replicas returned first, where N is a positive integer not less than half the number of application replicas, and take the replica return result corresponding to the largest proportion as the final return result; Alternatively, when the number of identical copy results received reaches a set threshold, the corresponding identical copy result will be used as the final result.

3. An airborne cloud computing control system in a radiation environment, characterized by: This includes a cloud computing platform and multiple task machines that are all connected to the cloud computing platform. The cloud computing platform is used for: Receive application deployment service requests from the service deployment provider; A service proxy is established based on the application deployment service request. After generating multiple application copies, the service proxy returns the service address to the service deployer. The service proxy generates multiple application copies in a number less than the total number of idle task machines, based on the configuration requirements of CPU and memory utilization. The number of application copies is an odd number greater than 3. Upon receiving a service execution request from the service deployment provider, application copies are transmitted one by one to mission machines distributed across different locations on the aircraft. The application copies are then deployed to appropriate mission machines based on a comprehensive analysis of mission machine response rates and distribution levels. Specifically, the process of deploying application copies to mission machines involves: calculating a distribution strategy with the maximum mission machine response rate as the first optimization objective and the minimum mission machine distribution level as the second optimization objective; and deploying multiple application copies one by one to corresponding idle mission machines according to the distribution strategy. Furthermore, all idle mission machines are sorted according to their response rates to obtain the order of priority for different mission machines. First, a priority value is assigned. All idle mission machines are sorted according to their dispersion, resulting in a second priority value for each mission machine. A final priority value is calculated based on the weights of the first and second priority values, and the mission machines ranked highest by the final priority value are selected to form a distributed deployment strategy. Multiple application copies are then deployed one by one to the corresponding idle mission machines according to the distributed deployment strategy. The dispersion of mission machines represents the uniformity of the selected mission machines' distribution throughout the entire aircraft deployment area. The ratio of the total aircraft deployment area to the number of selected mission machines is used as the coverage area of ​​a single mission machine, and the degree of overlap of all coverage areas represents the dispersion of mission machines. In addition, it receives the replica return results from multiple task machines, determines the final return result based on the similarity of all received replica return results, and transmits the final return result to the service deployment party; The task machine is used to perform calculations on the received application copy and output the copy return result.

4. The airborne cloud computing control system under radiation environment according to claim 3, characterized in that, The mission aircraft are distributed in a matrix arrangement at different positions on the aircraft in the horizontal plane.

5. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the airborne cloud computing control method under radiation environment as described in any one of claims 1-2.

6. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, can implement the airborne cloud computing control method under radiation conditions as described in any one of claims 1-2.

Images