A multi-aircraft scheduling system and method based on Kubernetes cloud computing power

By using a cloud computing power multi-aircraft scheduling system based on Kubernetes, combined with various load balancing strategies and dynamic switching algorithms, the system solves the problem of insufficient flexibility in complex tasks and improves system performance and stability.

CN119847761BActive Publication Date: 2026-11-10HUNAN EXCELLENT INTELLIGENT COMPUTING TECHNOLOGY CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202510015853.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-06
Publication Date
2026-11-10
Estimated Expiration
2045-01-06

AI Technical Summary

Technical Problem

Existing multi-aircraft scheduling systems lack flexibility and adaptability in scheduling algorithms and strategies when facing complex tasks. They cannot dynamically adjust according to real-time flight data and environmental changes, resulting in insufficient system performance and stability.

Method used

A cloud computing power multi-aircraft scheduling system based on Kubernetes is adopted, including a Kubernetes resource management module, a task receiving and parsing module, a load balancing strategy module, and a task scheduling module. By monitoring and dynamically adjusting the task allocation strategy in real time, combined with load balancing strategies based on weight, priority, resource utilization, geographical location, and response time, efficient task scheduling and system stability are achieved.

Benefits of technology

It improves the overall performance and stability of the system in complex mission scenarios, and can dynamically adjust according to the performance of the aircraft and mission requirements to ensure efficient use of system resources and mission continuity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119847761B_ABST
    Figure CN119847761B_ABST
Patent Text Reader

Abstract

This invention provides a multi-aircraft scheduling system based on Kubernetes (K8S) cloud computing power, including a Kubernetes resource management module, a task receiving and parsing module, a load balancing strategy module, and a task scheduling module. The signal terminal of the Kubernetes resource management module is connected to the signal terminal of the task receiving module. Through the resource management module, the system can more accurately understand the capabilities and limitations of each aircraft, thus providing basic data support for subsequent load balancing and task scheduling. The load balancing module formulates the optimal load balancing strategy based on the current task requirements and aircraft status information. In complex task scenarios, the dynamic switching algorithm can quickly calculate the optimal switching scheme based on the current status of the aircraft and task requirements, switching tasks from faulty or inefficient aircraft to other available aircraft, and then dynamically adjusting based on real-time flight data and environmental changes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to a scheduling system and method, specifically a multi-aircraft scheduling system and method based on K8S cloud computing power, belonging to the technical field of aircraft scheduling systems. Background Technology

[0002] A multi-aircraft scheduling system is a high-tech management platform specifically designed for managing and scheduling the flight plans and missions of multiple aircraft. It integrates multiple functions such as flight control, mission planning, real-time monitoring, data acquisition, and processing, significantly improving the efficiency and safety of aircraft operations. By integrating the flight plans of multiple aircraft, the multi-aircraft scheduling system achieves collaborative management and scheduling, ensuring flight safety and efficiency.

[0003] Existing multi-aircraft scheduling systems have relatively simple scheduling algorithms and strategies, which cannot meet the needs of complex tasks. This is because traditional scheduling algorithms, such as First-Come, First-Served (FCFS) and Shortest Job First (SJF), may perform well when handling a single aircraft or a simple task, but their limitations become apparent when facing a complex environment with multiple aircraft and multiple tasks. These algorithms often lack sufficient flexibility and adaptability and cannot be dynamically adjusted according to real-time flight data and environmental changes. Therefore, a multi-aircraft scheduling system and method based on Kubernetes cloud computing power is proposed. Summary of the Invention

[0004] In view of this, the present invention provides a multi-aircraft scheduling system and method based on K8S cloud computing power to solve or alleviate the technical problems existing in the prior art, and at least provides a beneficial option.

[0005] The technical solution of this invention is implemented as follows: a multi-aircraft scheduling system based on K8S cloud computing power, including a Kubernetes resource management module, a task receiving and parsing module, a load balancing strategy module and a task scheduling module, wherein the signal terminal of the Kubernetes resource management module is connected to the signal terminal of the task receiving module, and the signal terminal of the load balancing strategy module is connected to the signal terminals of the task adjustment module and the task receiving and parsing module respectively. The Kubernetes resource management module is used to monitor and manage resources in the Kubernetes cluster, including CPU, memory, storage and network. By monitoring resource usage in real time, it provides data support for load balancing strategies. The task receiving and parsing module is used to receive task requests from the aircraft and to parse and process the task requests. The load balancing strategy module is used to design load balancing strategies and dynamically adjust task allocation strategies based on task type, resource requirements, and cluster status using a dynamic switching algorithm. The load balancing strategy includes: Weight-based load balancing strategy: Assign different weights to nodes based on their resource availability and task requirements; Priority-based load balancing strategy: Set different priorities for tasks and schedule tasks according to the priorities; Load balancing strategy based on resource utilization: Real-time monitoring of node resource utilization and task scheduling based on resource utilization. Location-based load balancing strategy: Select the nearest node for task scheduling based on the aircraft's geographical location and mission requirements; The least-connections-based load balancing strategy monitors the current number of active connections on each server and assigns new requests to the server with the fewest current connections. Response time-based load balancing: Monitor the response time of each server and distribute new requests to the server with the shortest response time; The task scheduling module is used to schedule tasks to designated server nodes according to the current optimal load balancing strategy.

[0006] More preferably, the task scheduling module is equipped with a monitoring and fault tolerance mechanism to detect and handle server failures. When a server fails, the task scheduling module will redirect the task to other normal servers.

[0007] More preferably, the dynamic switching algorithm includes the following steps: Real-time monitoring: Collect performance metrics for each server, including CPU utilization, memory usage, network bandwidth utilization, response time, and number of active connections; Analyze performance indicators: Conduct in-depth analysis of the collected monitoring data to calculate the changing trends of each performance indicator and the relationships between them; Strategy Evaluation: Based on the analysis results, evaluate the applicability of each current load balancing strategy and present the evaluation results in the form of a report. The evaluation factors include the actual needs of the system, user habits, and the importance of the business. Comparing the advantages and disadvantages of different load balancing strategies: Based on the evaluation report, compare the advantages and disadvantages of each strategy, analyze the performance of each strategy in terms of performance indicators, and the impact on system performance and user experience. Strategy selection: Based on the comparison results, select the optimal load balancing strategy at present; Policy switching: Switching the load balancing system to a new optimal policy without interrupting service, including updating the load balancer configuration and adjusting the weight or priority of servers.

[0008] Further optimized components include a resource reservation module, a resource release module, and an execution module; The resource reservation module is used to reserve resources before task scheduling, and to reserve enough resources in advance for critical tasks or services. Resource reservation is implemented in a static or dynamic way. Static reservation is to allocate a fixed amount of resources in the system configuration, while dynamic reservation is to adjust the resource allocation according to the real-time load and system usage mode.

[0009] More preferably, the resource release module is used to release resources when the strategy is executed; The execution model is used to execute the optimal load balancing strategy.

[0010] Further preferred options include a user interaction module, a fault detection module, a security module, and a monitoring feedback module; The monitoring and feedback module is used to monitor the execution status of tasks and provide feedback on task progress and results to the user.

[0011] More preferably, the fault detection module is used to detect faults that occur in the system and automatically perform recovery operations, while recording log information during system operation.

[0012] More preferably, the security module is used to authenticate the user's identity and authorize permissions, preventing unauthorized users from accessing the system.

[0013] More preferably, the user interaction module is used to provide a user interface through which the user controls the system.

[0014] A multi-aircraft scheduling method based on Kubernetes cloud computing power includes the following steps: Resource management: Monitor and manage resources in a Kubernetes cluster, including CPU, memory, storage, and network. Mission reception and parsing: Receive mission requests from the aircraft, and parse and process the mission requests; Strategy allocation: The task allocation strategy is dynamically adjusted based on task type, resource requirements, and cluster status using a dynamic switching algorithm; Task scheduling: Based on the current optimal load balancing strategy, tasks are scheduled to the specified server nodes; Task execution: Execute the optimal load balancing strategy.

[0015] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: This invention integrates and manages all resources in the system through a resource management module, enabling real-time acquisition of aircraft status information. This module allows for a more precise understanding of each aircraft's capabilities and limitations, providing foundational data support for subsequent load balancing and task scheduling. The load balancing module formulates the optimal load balancing strategy based on current task requirements and aircraft status information. In complex task scenarios, the load balancing strategy module dynamically adjusts the strategy based on factors such as aircraft performance differences, task priorities, and flight paths to ensure overall system performance and stability. Furthermore, in complex task scenarios, a dynamic switching algorithm quickly calculates the optimal switching scheme based on the aircraft's current status and task requirements, switching tasks from faulty or inefficient aircraft to other available aircraft, and dynamically adjusting based on real-time flight data and environmental changes.

[0016] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a structural diagram of a multi-aircraft scheduling system based on K8S cloud computing power according to the present invention; Figure 2 This is a flowchart illustrating the steps of a multi-aircraft scheduling method based on K8S cloud computing power according to the present invention. Detailed Implementation

[0019] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0020] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] like Figures 1-2As shown, this embodiment of the invention provides a multi-aircraft scheduling system based on K8S cloud computing power, including a Kubernetes resource management module, a task receiving and parsing module, a load balancing strategy module, and a task scheduling module. The signal terminal of the Kubernetes resource management module is connected to the signal terminal of the task receiving module, and the signal terminal of the load balancing strategy module is connected to the signal terminals of the task adjustment module and the task receiving and parsing module, respectively. The Kubernetes resource management module is used to monitor and manage resources in a Kubernetes cluster, including CPU, memory, storage, and network. By monitoring resource usage in real time, it provides data support for load balancing strategies. K8S is Kubernetes. Kubernetes cloud computing power refers to the computing resources managed and scheduled using the Kubernetes platform. These resources are usually provided by cloud computing platforms. As an open-source container orchestration and management tool, Kubernetes can automatically deploy, scale, and manage containerized applications, thereby effectively utilizing cloud computing resources. The resource management module is responsible for integrating and managing all resources in the system, including aircraft, sensors, and communication equipment. This module can acquire real-time status information of aircraft, such as location, speed, and remaining battery power, and classify and prioritize aircraft based on this information. Through the resource management module, the system can more accurately understand the capabilities and limitations of each aircraft, thereby providing basic data support for subsequent load balancing and task scheduling. The task receiving and parsing module is used to receive task requests from the aircraft, parse and process the task requests, and ensure that the task requests can be correctly understood and processed by the system, laying the foundation for subsequent task scheduling and resource allocation. The load balancing strategy module is used to design load balancing strategies. It dynamically adjusts the task allocation strategy based on task type, resource requirements and cluster status using a dynamic switching algorithm to ensure load balancing and resource optimization. In complex mission scenarios, the load balancing strategy module can dynamically adjust the load balancing strategy based on factors such as aircraft performance differences, mission priority, and flight path: When an aircraft has good performance and a low current load, it can be assigned more tasks. When a particular aircraft has poor performance or a high current load, its task allocation is reduced to ensure the overall performance and stability of the system. Load balancing strategies include: Weighted load balancing strategy: Based on the resource status and task requirements of nodes, different weights are assigned to nodes to achieve reasonable task distribution. The basis for formulating a weighted load balancing strategy is based on server resources such as processing power, memory, storage, and network bandwidth, as well as business needs and priorities. The weight value reflects the server's processing power and priority. Servers with higher weights will receive more requests. Priority-based load balancing strategy: Different priorities are set for tasks, and tasks are scheduled according to the priorities to ensure that high-priority tasks are processed first. The basis for specifying the priority-based load balancing strategy is to allocate different priorities to traffic or applications based on the priority requirements of different traffic or business applications; high-priority traffic or applications will get services first, ensuring the stability and response speed of critical business applications. Load balancing strategy based on resource utilization: Real-time monitoring of node resource utilization, and task scheduling based on resource utilization to avoid resource overload and waste; Geographic location-based load balancing strategy: Select the nearest node for task scheduling based on the aircraft's geographical location and mission requirements to reduce transmission latency and costs; The least-connections-based load balancing strategy monitors the current number of active connections on each server and assigns new requests to the server with the fewest current connections to ensure that each server can process requests efficiently, reduce response time, make full use of the resources of all servers in the cluster, and avoid resource waste. Response time-based load balancing: Monitor the response time of each server and distribute new requests to the server with the shortest response time to ensure that requests are forwarded to the best-performing server, thereby reducing response time; The six load balancing strategies—weight-based load balancing, priority-based load balancing, resource utilization-based load balancing, geolocation-based load balancing, least connections-based load balancing, and response time-based load balancing—are designed to address different system requirements and business scenarios, thereby optimizing performance, improving service quality, and ensuring efficient resource utilization. Specifically, weight-based load balancing strategies take into account the server's processing capacity, resources, and business needs, and assign weight values ​​to the server to determine the number of requests it can handle. Priority-based strategies allocate requests according to traffic or application priority, ensuring that critical business processes are processed first. A resource utilization-based strategy monitors server resource usage in real time and dynamically adjusts request allocation to avoid overload and waste. A location-based strategy distributes requests to the nearest server based on the user's location, reducing latency and improving service quality. The least-connection strategy distributes requests to the server with the fewest connections, which is suitable for long-connection services to balance the load. Response time-based strategies measure server response time in real time and assign requests to the server that is expected to respond the fastest, thereby optimizing the user experience. The above strategies can be selected and dynamically adjusted based on system requirements and monitoring data to achieve the best load balancing effect.

[0022] The task scheduling module schedules tasks to designated server nodes based on the current optimal load balancing strategy. Through reasonable task allocation, it ensures that each server or resource in the system can bear the load evenly, avoiding the situation where some servers are overloaded while other servers are idle. Load balancing helps improve the overall performance and resource utilization of the system, while reducing response time. The task scheduling module is equipped with monitoring and fault tolerance mechanisms to detect and handle server failures. When a server fails, the task scheduling module will redirect tasks to other normal servers to ensure service continuity.

[0023] In one embodiment, the dynamic switching algorithm includes the following steps: Real-time monitoring: Collect performance metrics for each server, including CPU utilization, memory usage, network bandwidth utilization, response time, and active connections. The monitoring data needs to be collected and analyzed in real time to quickly respond to changes in system performance. Analyze performance indicators: Conduct in-depth analysis of the collected monitoring data to calculate the changing trends of each performance indicator and the relationships between them; Strategy Evaluation: Based on the analysis results, evaluate the applicability of each current load balancing strategy and present the evaluation results in the form of a report. The evaluation factors include the actual needs of the system, user habits, and the importance of the business. For example, in scenarios that require fast response and high availability, the load balancing strategy based on response time is more advantageous; while when handling a large number of short connection requests, the load balancing strategy based on the fewest connections is more suitable. Comparing the advantages and disadvantages of different load balancing strategies: Based on the evaluation report, compare the advantages and disadvantages of each strategy, analyze the performance of each strategy in terms of performance indicators, and the impact on system performance and user experience. Strategy selection: Based on the comparison results, select the current optimal load balancing strategy. The selection of the optimal strategy may be based on multiple factors, including minimizing response time, maximizing throughput, and optimizing resource utilization. Policy switching: Switching the load balancing system to a new optimal policy without interrupting service, including updating the load balancer configuration and adjusting the server weights or priorities; Dynamic switching algorithms are an important mechanism in multi-aircraft scheduling systems to deal with emergencies and mission changes. When there are situations such as aircraft failures, mission priority changes, or flight path adjustments in the system, dynamic switching algorithms can adjust the mission allocation and flight path of aircraft in real time to ensure the overall performance and stability of the system. The dynamic switching algorithm can quickly calculate the optimal switching scheme based on the current state of the aircraft and the mission requirements, and switch the mission from a faulty or inefficient aircraft to other available aircraft. At the same time, the algorithm can also consider the flight characteristics of the aircraft and the correlation between the missions to ensure that the mission can be executed smoothly after the switch.

[0024] In the above algorithm, "strategy evaluation" is a key step in ensuring the efficient operation of the system, and it specifically includes the following steps: I. Data Collection: Monitoring data: Real-time collection of load balancer performance metrics, including CPU utilization, memory utilization, network traffic, response time, and throughput, through monitoring tools; Task data: Records the execution time, resource consumption, and priority of each task; Server status: Obtain the server's hardware configuration, current load, and processing capacity; II. Strategy Definition: Define the load balancing strategy used in the current system, including weight-based load balancing, priority-based load balancing, round-robin, and least connections. Understand how each strategy works and in which it is applicable; III. Performance Analysis: Based on monitoring data, analyze the performance of each strategy under the current load, compare the response time, throughput, and resource utilization under different strategies, and identify performance bottlenecks and potential problems. IV. Strategy Applicability Assessment: Based on the performance analysis results, evaluate the applicability of each strategy in the current system, taking into account task type, server configuration, load variation factors, and select the optimal load balancing strategy.

[0025] V. Strategy Adjustment and Optimization: Based on the evaluation results, the load balancing strategy was adjusted and optimized. The main influencing factors of the evaluation results include performance indicators and system status indicators. By analyzing these indicators, the load balancing strategy can be adjusted and optimized. Specifically: The factors influencing performance metrics include response time, throughput, resource utilization, and error rate. The following is a detailed analysis of these factors: Response time: If the response time increases significantly, it indicates that the current strategy has not adequately considered the server's processing capacity or network latency when allocating requests. Throughput: A decrease in throughput indicates a bottleneck in the system, such as an overloaded single server or insufficient network bandwidth; Resource utilization: Uneven resource utilization indicates that the strategy has failed to effectively distribute the load. Error rate: High error rates are often caused by improper request allocation due to policy issues or server malfunctions; The factors influencing system status indicators include server status, network conditions, and task type. The following is a detailed analysis of these factors: Server status: The server's hardware configuration, current load, and processing capacity are important for policy adjustments; Network conditions: Network latency, bandwidth limitations, and other network factors can affect the effectiveness of load balancing strategies; Task type: Different tasks have different resource requirements, such as compute-intensive tasks and I / O-intensive tasks.

[0026] During system operation, the load balancing strategy can be adjusted and optimized based on the evaluation results. The adjustment and optimization of the load balancing strategy is a continuous process that can be flexibly adjusted according to the evaluation results and actual needs. By continuously optimizing the load balancing strategy, improving resource utilization and network performance, the system can maintain high performance and stability when facing ever-changing load demands. Load balancing strategy adjustment and optimization includes two aspects: strategy adjustment, resource optimization, network optimization, and periodic evaluation and adjustment, as well as emergency response mechanisms. Strategy adjustment includes dynamic weight adjustment, algorithm optimization, task analysis, and priority handling; resource optimization includes resource reservation and release; network optimization includes network load balancing and bandwidth management; periodic evaluation and adjustment includes periodic monitoring and strategy iteration; and emergency response mechanisms include fault detection and recovery, and disaster recovery backup. Details are as follows: 1. Strategy Adjustment Dynamic weight adjustment: The weight of the server is dynamically adjusted based on the server's real-time load and performance to ensure that requests are distributed more evenly across the servers. Algorithm optimization: Introduce more advanced load balancing algorithms, including consistent hashing and minimum active connections, to adapt to different load scenarios; Task classification and prioritization: Classify tasks and apply different processing strategies according to their priority to ensure that high-priority tasks are processed first. 2. Resource optimization Resource reservation: Reserve necessary resources for mission-critical tasks to ensure stable performance under high load conditions; Resource release: Release idle or no longer needed resources in a timely manner to improve resource utilization; 3. Network optimization Network load balancing: Implementing load balancing at the network layer, including using DNS round-robin and HTTP redirection methods to distribute network traffic; Bandwidth management: Allocate network bandwidth reasonably according to business needs to avoid network congestion; 4. Regular evaluation and adjustment Regular monitoring: Establish a regular monitoring mechanism to continuously collect and analyze performance indicators and system status information; Strategy iteration: Continuously optimize the load balancing strategy based on monitoring results to adapt to load changes and system upgrades; 5. Emergency Response Mechanism: Fault Detection and Recovery: Establish a rapid response mechanism to promptly detect and handle system faults, ensuring that the system can quickly return to normal operation; Disaster recovery backup: Develop a disaster recovery backup plan to ensure that you can quickly switch to backup resources when critical servers or networks fail.

[0027] In one embodiment, it further includes a resource reservation module, a resource release module, and an execution module; The resource reservation module is used to reserve resources before task scheduling, ensuring sufficient resources are available for critical tasks or services in advance. Resource reservation can be implemented statically or dynamically. Static reservation allocates a fixed amount of resources in the system configuration, while dynamic reservation adjusts resource allocation based on real-time load and system usage patterns. The resource release module is used to release resources when the policy is executed. By employing reasonable resource reservation and release strategies, we can avoid resource waste and idleness. When resources are scarce, we can prioritize meeting the needs of critical tasks or services; when resources are plentiful, we can allocate the remaining resources to other tasks or services. The execution model is used to execute the optimal load balancing strategy.

[0028] In one embodiment, it further includes a user interaction module, a fault detection module, a security module, and a monitoring feedback module; The monitoring and feedback module is used to monitor the execution status of tasks and provide feedback on task progress and results to users to improve user experience, enabling users to understand the task execution status in a timely manner, which facilitates subsequent operations and adjustments. When monitoring the aircraft dispatching system, the monitoring feedback module employs the following steps: Monitoring target setting: First, clarify the monitoring targets of the task monitoring and feedback module, including the status of the aircraft, the progress of task execution, and the utilization of system resources. In a multi-aircraft scheduling system, each aircraft may have different tasks and targets, so the module needs to be able to distinguish and monitor the specific tasks of each aircraft. Data acquisition and collection: Real-time collection of key status data such as the aircraft's position, speed, altitude, and attitude through sensors and communication equipment; recording the start time, end time, and execution phase information of the mission, as well as various parameters and results during the mission execution process; monitoring the usage of system resources such as CPU, memory, and network bandwidth to ensure that system resources are allocated and utilized reasonably. Data processing and analysis: Using data analysis algorithms and models, real-time data is processed and analyzed to extract key information, including abnormal states of the aircraft and bottlenecks in mission execution. Then, based on historical and real-time data, machine learning algorithms are used to predict trends and identify potential problems and risks in advance. Alarms and Reminders: When an abnormal aircraft status, mission failure, or insufficient system resources are detected, the monitoring feedback module automatically triggers the alarm mechanism to remind the user through sound, light, SMS, etc. After the mission is completed, the monitoring feedback module generates a detailed mission feedback report, including the results of the mission, the problems encountered, and the process of solving them. The user can evaluate and summarize the mission performance based on the report. Optimization and Adjustment: Based on monitoring and analysis results, optimize and adjust the aircraft scheduling strategy and task allocation strategy to improve the overall performance and efficiency of the system. For system vulnerabilities and performance bottlenecks discovered during the monitoring process, upgrade and repair the system in a timely manner to ensure the stability and reliability of the system. Multi-aircraft collaborative monitoring: In a multi-aircraft scheduling system, the monitoring and feedback module enables information sharing and collaborative operation among aircraft by building a communication network and data sharing mechanism between them. At the same time, the monitoring and feedback module can also handle conflicts and competition among multiple aircraft to ensure the overall performance and efficiency of the system.

[0029] In one embodiment, the fault detection module is used to detect faults in the system and automatically perform recovery operations, while recording log information during system operation, thereby improving the reliability and stability of the system and ensuring that tasks can be handled and recovered in a timely manner when faults occur.

[0030] In one embodiment, the security module is used to authenticate and authorize users, preventing unauthorized users from accessing the system and thus protecting the security of system data and resources.

[0031] In one embodiment, the user interaction module provides a user interface through which users control the system, facilitating operation and management, improving user experience, and reducing the difficulty for users to learn and use the system.

[0032] A multi-aircraft scheduling method based on Kubernetes cloud computing power includes the following steps: Resource management: Monitor and manage resources in a Kubernetes cluster, including CPU, memory, storage, and network. Mission reception and parsing: Receive mission requests from the aircraft, and parse and process the mission requests; Strategy allocation: The task allocation strategy is dynamically adjusted based on task type, resource requirements, and cluster status using a dynamic switching algorithm; Task scheduling: Based on the current optimal load balancing strategy, tasks are scheduled to the specified server nodes; Task execution: Execute the optimal load balancing strategy.

[0033] In operation, this invention monitors and manages resources in the Kubernetes cluster, including CPU, memory, storage, and network, through the Kubernetes resource management module. It receives and processes task requests from the aircraft through the task receiving and parsing module. The load balancing strategy module dynamically adjusts the task allocation strategy based on task type, resource requirements, and cluster status using a dynamic switching algorithm. Load balancing strategies include weight-based, priority-based, resource utilization-based, geolocation-based, least-connections-based, and response-time-based strategies. The task scheduling module schedules tasks to designated server nodes according to the current optimal load balancing strategy, and then the execution module executes the optimal load balancing strategy.

[0034] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-aircraft scheduling system based on Kubernetes cloud computing power, comprising a Kubernetes resource management module, a task receiving and parsing module, a load balancing strategy module, and a task scheduling module, characterized in that: The signal terminal of the Kubernetes resource management module is connected to the signal terminal of the task receiving and parsing module, and the signal terminal of the load balancing strategy module is connected to the signal terminals of the task scheduling module and the task receiving and parsing module, respectively. The Kubernetes resource management module is used to monitor and manage resources in the Kubernetes cluster, including CPU, memory, storage and network. By monitoring resource usage in real time, it provides data support for load balancing strategies. The task receiving and parsing module is used to receive task requests from the aircraft and to parse and process the task requests. The load balancing strategy module is used to design load balancing strategies and dynamically adjust task allocation strategies based on task type, resource requirements, and cluster status using a dynamic switching algorithm. The dynamic switching algorithm, The following steps are included: Real-time monitoring: Collect performance metrics for each server, including CPU utilization, memory usage, network bandwidth utilization, response time, and number of active connections; Performance Metric Analysis: In-depth analysis of collected monitoring data is conducted to calculate the trends and relationships between various performance metrics. Strategy Evaluation: Based on the analysis results, the applicability of each current load balancing strategy is evaluated, and the evaluation results are presented in a report. Factors influencing the evaluation include the system's actual needs, user habits, and the importance of the business. Strategy Comparison: The advantages and disadvantages of each load balancing strategy are compared based on the evaluation report, analyzing the performance metrics of each strategy and its impact on system performance and user experience. Strategy Selection: Based on the comparison results, the optimal load balancing strategy is selected. Strategy Switching: Without interrupting service, the load balancing system is switched to the new optimal strategy, including updating the load balancer configuration and adjusting server weights or priorities. The load balancing strategy includes: Weight-based load balancing strategy: Assign different weights to nodes based on their resource availability and task requirements; Priority-based load balancing strategy: Set different priorities for tasks and schedule tasks according to the priorities; Load balancing strategy based on resource utilization: Real-time monitoring of node resource utilization and task scheduling based on resource utilization. Location-based load balancing strategy: Select the nearest node for task scheduling based on the aircraft's geographical location and mission requirements; The least-connections-based load balancing strategy monitors the current number of active connections on each server and assigns new requests to the server with the fewest current connections. Response time-based load balancing: Monitor the response time of each server and distribute new requests to the server with the shortest response time; The task scheduling module is used to schedule tasks to specified server nodes according to the current optimal load balancing strategy. It also includes a resource reservation module, a resource release module, and an execution module; The resource reservation module is used to reserve resources before task scheduling, and reserve enough resources in advance for critical tasks or services. Resource reservation is implemented in a static or dynamic way. Static reservation is to allocate a fixed amount of resources in the system configuration, while dynamic reservation is to adjust the resource allocation according to the real-time load and system usage mode. The resource release module is used to release resources when the strategy is executed; The execution module is used to execute the optimal load balancing strategy; The task scheduling module is equipped with a monitoring and fault tolerance mechanism to detect and handle server failures. When a server fails, the task scheduling module will redirect the task to other normal servers. It also includes a user interaction module, a fault detection module, a security module, and a monitoring and feedback module; The monitoring and feedback module is used to monitor the execution status of the task and provide feedback on the task progress and results to the user. The fault detection module is used to detect faults in the system, automatically perform recovery operations, and record log information during system operation.

2. The multi-aircraft scheduling system based on Kubernetes cloud computing power according to claim 1, characterized in that: The security module is used to authenticate users and authorize their permissions; unauthorized users cannot access the system.

3. A multi-aircraft scheduling system based on Kubernetes cloud computing power according to claim 1, characterized in that: The user interaction module is used to provide a user interface through which users can control the system.

4. A multi-aircraft scheduling method based on Kubernetes (K8S) cloud computing power, applied to the multi-aircraft scheduling system based on K8S cloud computing power as described in any one of claims 1-3, characterized in that, Includes the following steps: Resource management: Monitor and manage resources in a Kubernetes cluster, including CPU, memory, storage, and network. Task reception and parsing: Receives task requests from the aircraft and parses and processes the task requests; Strategy allocation: The task allocation strategy is dynamically adjusted based on task type, resource requirements, and cluster status using a dynamic switching algorithm; Task scheduling: Based on the current optimal load balancing strategy, tasks are scheduled to the specified server nodes; Task execution: Execute the optimal load balancing strategy.

Citation Information

Patent Citations

  • Intelligent load balancing method and device and storage medium

    CN112532743A

  • Kubernetes-based unmanned aerial vehicle task scheduling and fault processing system and method

    CN117389130A

  • Cloud computing scheduling system and cloud computing scheduling method

    CN118747121A