Resource allocation method and device for inland waterway vessel area controller

By establishing a resource database and a resource prediction model, and dynamically adjusting resource allocation, the problem of coordinating the mission requirements of intelligent inland waterway vessels was solved, achieving efficient resource utilization and successful mission completion.

CN114510349BActive Publication Date: 2024-11-12WUHAN UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210007951.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-04
Publication Date
2024-11-12
Estimated Expiration
2042-01-04

AI Technical Summary

Technical Problem

The existing distributed architecture cannot efficiently coordinate the mission requirements of inland waterway intelligent vessels, resulting in improper resource allocation and an inability to meet the service quality requirements for mission execution and function display.

Method used

By establishing a resource database, resource prediction model, and task classification algorithm for inland waterway vessel area controllers, resource allocation is dynamically adjusted to meet task requirements. This includes resource coding, sparse coding processing, support vector machine model training, and performance prediction algorithms to optimize resource supply and ensure successful task completion.

Benefits of technology

It enabled the successful completion of tasks with minimal resource supply while meeting service quality requirements, thereby improving resource utilization and task execution efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114510349B_ABST
    Figure CN114510349B_ABST
Patent Text Reader

Abstract

The present invention relates to a resource allocation method for an inland river vessel area controller, which is characterized in that it includes the following steps: representing and describing all resources within the inland river intelligent vessel area controller architecture to establish a resource library; establishing a resource prediction model; classifying tasks and predicting the required resources based on the resource prediction model; determining whether to execute the task based on the resource prediction; calling appropriate resources to execute the task based on the resource prediction and monitoring in a timely manner, and dynamically adjusting the resources for executing the task; and optimizing the resource prediction model based on the situation after the task is completed. The present invention first establishes a resource prediction model, classifies tasks and predicts the required resources based on the resource prediction model, and then calls resources to execute tasks based on the resource prediction; it can enable the task to be successfully completed with the minimum resource supply and meet the service quality requirements for task execution; it is conducive to the full utilization of resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of hydroacoustic positioning, and in particular to a resource allocation method and device for an inland river vessel area controller. Background Art

[0002] The development trend of the smart ship industry is intelligent, green and software-defined ships. The development of intelligence and electrification has greatly triggered the number of sensors, data volume and processing volume of smart ships.

[0003] This is a load that the existing distributed architecture cannot handle, and the distributed resource controller cannot efficiently meet the functional needs of inland smart ships.

[0004] With the changes brought about by the physical and functional architecture of inland river intelligent ships, the amount of data and the total types of sensors have increased. There is an urgent need to develop a new resource allocation method to manage the entire ship resources of inland river intelligent ships and dynamically schedule resources according to the navigation needs of inland river intelligent ships, so as to ensure the service quality of inland river intelligent ships' task execution and function display. Summary of the invention

[0005] The purpose of the present invention is to provide a resource allocation method and device for an inland river vessel area controller in order to solve the problem that the existing distributed architecture cannot coordinate the ship mission requirements.

[0006] The technical solution adopted by the present invention is: a resource allocation method for an inland river vessel area controller, comprising the following steps:

[0007] Represent and describe all resources in the regional controller architecture of inland river intelligent ships and establish a resource library;

[0008] Establish resource forecasting models;

[0009] Classify tasks and predict required resources based on resource forecasting models;

[0010] Determine whether to execute the task based on resource forecast;

[0011] According to resource forecast, appropriate resources are allocated to perform the task and timely monitored, and the resources used to perform the task are dynamically adjusted;

[0012] Optimize resource forecasting models based on post-task completion.

[0013] Furthermore, all resources in the inland river intelligent ship regional controller architecture are represented and described, and a resource library is established, specifically:

[0014] The resources of inland river smart ships are encoded using self-compiled uniform resource locators and encoding technology:

[0015] Described using Extensible Markup Language and Resource Description Framework;

[0016] Use ontology to describe the connections between resources;

[0017] Build a resource library with resources that complete the description;

[0018] Monitor the resource status in the resource library in real time and mark idle resources as idle.

[0019] Furthermore, a resource prediction model is established, specifically:

[0020] Establish a historical task library with completed tasks of known types, and collect resource consumption snapshots of tasks in the historical task library;

[0021] Use sparse coding to process resource snapshots, quantize them into "words", and obtain a resource dictionary;

[0022] Use the resource dictionary as training data to train a linear multi-classification support vector machine SVM;

[0023] A resource prediction model is established using resource dictionary and support vector machine (SVM).

[0024] Furthermore, the tasks are classified and the required resources are predicted based on the resource prediction model, specifically:

[0025] Classify the obtained tasks based on the resource prediction model;

[0026] Determine the amount of pre-allocated resources for the task based on the resource prediction model;

[0027] The performance prediction algorithm based on the task execution frequency predicts the performance index of the task under the current pre-allocated resource amount;

[0028] Use binary search and control variable methods to adjust the resource supply of the task and determine the minimum resources required to complete the task successfully.

[0029] Furthermore, the obtained tasks are classified based on the resource prediction model, specifically:

[0030] Intercept a small portion of the task's input and run it as a probe:

[0031] Collect resource consumption snapshots during the probe operation, process the resource snapshots with sparse coding, and quantize them into "words".

[0032] The “word” is input into the SVM classifier in the resource prediction model to obtain the task category.

[0033] Furthermore, the amount of pre-allocated resources for the task is determined according to the resource prediction model, specifically:

[0034] Search the historical task library by task category, call up historical tasks of the same task category, and obtain resource consumption snapshots of historical tasks;

[0035] The average resource consumption of historical tasks is obtained as the pre-allocated resource amount of the task.

[0036] Furthermore, the performance prediction algorithm based on the task execution frequency predicts the performance index of the task being executed under the current pre-allocated resources, specifically:

[0037] Provide the input parameters and configuration parameters of the task and generate the task description function X new ,

[0038] X new = {detailed input information A, QoS performance requirements Q, resource consumption mode F t}, where the detailed input information A of the task includes task size, task type, etc.;

[0039] Increase the value of adjacent tasks K one by one, using x n1 ;x n2 ;…;x nk represents the K neighbors of the task, d1; d2; ...; d k represents their Euler distance to the task. When the density f(k) around the new task reaches a maximum value for the first time, the K value at this time is used as the most suitable number of nearest neighbors for prediction;

[0040] Calculate the contribution ψ of different neighbor tasks i ,

[0041] Calculate the weighted function to predict the performance of new tasks.

[0042] Furthermore, the density f(k) is calculated as

[0043] Furthermore, the contribution ψ i The calculation formula is The weighting function is

[0044] The present invention also provides a device for locating garbage secretly discharged into water by ships, comprising:

[0045] The resource description unit is used to represent and describe all resources in the inland river intelligent ship area controller architecture and establish a resource library;

[0046] A resource prediction model building unit, used for building a resource prediction model;

[0047] A parsing unit, used to parse the task and predict the required resources based on the resource prediction model;

[0048] A task confirmation unit, used to determine whether to execute the task according to resource prediction;

[0049] The task dynamic execution unit is used to call appropriate resources to execute the task according to resource prediction and timely monitor and dynamically adjust the resources for executing the task;

[0050] The optimization unit is used to optimize the resource prediction model according to the completion status of the task.

[0051] The present invention proposes a resource allocation method and device for an inland vessel area controller, which first establishes a resource prediction model, classifies tasks and predicts the required resources based on the resource prediction model, and then calls resources to execute tasks according to the resource prediction; it can enable tasks to be successfully completed with a minimum resource supply and meet the service quality requirements of task execution; it is conducive to the full utilization of resources.

[0052] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0054] Figure 1 Shown is a schematic diagram of the steps of a resource allocation method for an inland vessel area controller provided by the present invention. DETAILED DESCRIPTION

[0055] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention is described in more detail by way of example with reference to the accompanying drawings in the following paragraphs. The advantages and features of the present invention will become clearer according to the following description and claims. It should be noted that the drawings are all in a very simplified form and are not in precise proportions, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.

[0056] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly mounted on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component at the same time. When a component is considered to be "fixed to" another component, it may be directly fixed on the other component or there may be a central component at the same time.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0058] Example 1

[0059] The following is a description of the scanning device for multiple diseases provided by the present invention in conjunction with the accompanying drawings:

[0060] See also Figure 1 , a resource allocation method for an inland river vessel area controller provided by the present invention comprises the following steps:

[0061] S1. Represent and describe all resources in the inland river intelligent ship regional controller architecture and establish a resource library;

[0062] S2. Establish resource prediction model;

[0063] S3, classify the tasks and predict the required resources based on the resource prediction model;

[0064] S4, determining whether to execute the task based on resource forecast;

[0065] S5. According to the resource forecast, appropriate resources are allocated to perform the task and timely monitored, and the resources for performing the task are dynamically adjusted;

[0066] S6. Optimize the resource prediction model based on the situation after task completion.

[0067] Compared with the prior art, the present invention proposes a resource allocation method for an inland vessel area controller, which first predicts the resources required for a task and then calls for reasonable resources to perform the task; it can optimize the matching of tasks with the used resources and maximize the utilization of resources while ensuring the completion of tasks.

[0068] Specifically, step S1 includes:

[0069] S11. Encode the resources of the inland river intelligent ship using the self-compiled uniform resource locator and encoding technology:

[0070] S12. Describe using extensible markup language and resource description framework;

[0071] S13. Use ontology to describe the connections between resources;

[0072] S14, establishing a resource library with the resources that complete the description;

[0073] S15. Monitor the resource status in the resource library in real time, and mark idle resources as idle.

[0074] In step S1, the semantic description of resources is completed through clear logical language models and specifications, and a resource library is established to facilitate subsequent matching and calling.

[0075] Specifically, step S2 includes:

[0076] S21, establishing a historical task library with completed tasks of known types, and collecting resource consumption snapshots of tasks in the historical task library;

[0077] S22, using sparse coding to process the resource snapshot, quantizing it into "words", and obtaining a resource dictionary;

[0078] S23, using the resource dictionary as training data, training a linear multi-classification support vector machine SVM;

[0079] S24. Establish a resource prediction model using resource dictionary and support vector machine (SVM).

[0080] Specifically, step S3 includes:

[0081] S31. classifying the obtained tasks based on the resource prediction model;

[0082] S32, determining the amount of pre-allocated resources for the task according to the resource prediction model;

[0083] S33, predicting the performance index of the task to be executed under the current pre-allocated resource amount using a performance prediction algorithm based on the task execution frequency;

[0084] S34. Use binary search and control variable methods to adjust the resource supply of the task and determine the minimum resources required to successfully complete the task.

[0085] An important prerequisite for reasonably and effectively arranging task scheduling and resource distribution strategies is to roughly understand the resource requirements of the tasks. Reasonable classification of tasks can improve the accuracy of resource demand prediction. Therefore, before predicting the resource requirements of tasks, it is necessary to first determine their categories, then search for historical execution records of tasks of the same category in the database, establish relevant models, and predict the resource requirements of the tasks to be executed.

[0086] From the perspective of traffic operation and management, the resource requirements of computing tasks under the navigation status of inland intelligent ships are predicted. Under the premise of ensuring the service quality of system service objects, the resource supply is minimized and the service object and system overhead are reduced. At the same time, it is also used to guide the traffic system managers to implement task scheduling and resource allocation.

[0087] Specifically, step S31 includes:

[0088] S311. Intercept a small part of the task input and run it as a probe:

[0089] S312, during the operation of the probe, resource consumption snapshots are collected, resource snapshots are processed using sparse coding, and quantized into "words",

[0090] S313, inputting the “word” into the SVM classifier in the resource prediction model to obtain the task category.

[0091] Without professional guidance, ordinary users do not understand service quality indicators, let alone how to express their service quality requirements in professional terms. They often use natural language to describe service quality requirements, such as high definition, smoothness, etc. Therefore, constructing an SVM classifier can transform the natural language description of service quality requirements into a professional description that meets the standards.

[0092] Specifically, step S32 includes:

[0093] S321, searching the historical task library by task category, calling up historical tasks of the same task category, and obtaining a resource consumption snapshot of the historical tasks;

[0094] S322. Obtain an average value of resource consumption of historical tasks as the pre-allocated resource amount of the task.

[0095] Specifically, step S33 includes:

[0096] S331, provide input parameters and configuration parameters of the task, generate task description function X new ,

[0097] X new = {detailed input information A, QoS performance requirements Q, resource consumption mode F t}, where the detailed input information A of the task includes task size, task type, etc.;

[0098] S332, increase the value of adjacent tasks K one by one, using x n1 ;x n2 ;…;x nk represents the K neighbors of the task, d1; d2; ...; d k represents their Euler distance to the task. When the density f(k) around the new task reaches a maximum value for the first time, the K value at this time is used as the most suitable number of nearest neighbors for prediction;

[0099] S333, calculate the contribution of different neighbor tasks ψ i ,

[0100] S334. Calculate the weighted function and predict the performance of the new task.

[0101] Specifically, the formula of density f(k) in step S332 is

[0102] Specifically, in step S333, the contribution ψ i The calculation formula is

[0103] Specifically, the weighting function in step S334 is

[0104] The present invention designs a performance prediction algorithm based on task execution frequency. Given a task and its input and resource supply, we can use the algorithm to predict the performance index of the task. When we need to predict the resource requirements of a task, we first pre-allocate a certain amount of resources to the task based on the historical execution records. Then, with the pre-allocated resources and the input information of the task, we use the performance prediction algorithm based on task execution frequency to predict its performance index.

[0105] Gradually increase the number of neighboring tasks K that are calculated, because according to the neighbor hypothesis, there are similar features between a task instance and its surrounding tasks. According to this principle, first find several task neighbors of the task to be predicted, and then predict the performance indicators of the task to be predicted after execution based on the execution performance indicators of these neighbors, such as: execution time, maximum memory usage, communication overhead, read and write speed, etc. Calculate the distance from the K neighboring tasks to the new task instance and the density around the new task. When the density around the new task reaches the maximum value, the number of neighbors is used as the most suitable number of neighbors for prediction. According to the different contributions of different neighboring tasks to the prediction, a weighted function is designed to measure the sharing degree, so as to obtain a weighted prediction function to predict the performance of the new task.

[0106] Next, we use binary search and control variable methods to adjust the resource supply of the task. If the predicted performance indicators cannot meet the service quality requirements of task execution, the resource supply will be continuously increased until the service quality requirements of task execution are met. Otherwise, the resource supply will be reduced so that the task can be successfully completed with the minimum resource supply and meet the service quality requirements of task execution.

[0107] Specifically, step S4 includes:

[0108] S41, counting resources marked as idle in the resource library;

[0109] S42: Compare whether the idle resources are greater than the predicted resources. If the idle resources are greater than the predicted resources, determine to execute the task and execute step S5.

[0110] After the task performs resource demand forecasting, the idle resources in the system are observed. If the predicted resource demand can be met, a service agreement will be automatically generated with the end user, including service fees and violation penalty clauses. If the user also agrees to the generated service agreement, the task will be executed. If the idle resources in the system cannot meet the predicted resource demand, the task will be shelved or suspended.

[0111] S5. According to the resource forecast, appropriate resources are allocated to perform the task and monitored in real time, and the resources for performing the task are dynamically adjusted;

[0112] S6. Optimize the resource prediction model based on the situation after task completion.

[0113] Specifically, step S5 includes:

[0114] S51, according to the resource prediction, appropriate resources are retrieved as the execution library to execute the task;

[0115] S52, real-time monitoring of the usage of various resources in the execution library during task execution; when all resources in the execution library are used, resources are added to the execution library; when idle resources appear in the execution library, idle resources are removed from the execution library;

[0116] S53. Repeat step S52 until the task execution is completed.

[0117] The accuracy of the resource demand prediction algorithm cannot be completely accurate. On the other hand, the demand for resources during the execution of the task is constantly changing. Therefore, the present invention designs a dynamic adjustment step to dynamically adjust the resource supply according to the actual situation (too much resources for a long time or insufficient resources).

[0118] Specifically, step S6 includes:

[0119] S61, counting the number of resources consumed when the task is completed, collecting the task's resource consumption snapshot and storing it in the historical task library with the task type;

[0120] S62. Use set X to represent a resource consumption snapshot, S represents the number of all resource consumption snapshots in the database, and use the Kmeans dictionary learning algorithm to obtain the dictionary V and the quantization matrix U.

[0121] The present invention also provides a resource allocation device for an inland river vessel area controller, comprising:

[0122] The resource description unit is used to represent and describe all resources in the inland river intelligent ship area controller architecture and establish a resource library;

[0123] A resource prediction model building unit, used for building a resource prediction model;

[0124] A parsing unit, used to parse the task and predict the required resources based on the resource prediction model;

[0125] A task confirmation unit, used to determine whether to execute the task according to resource prediction;

[0126] The task dynamic execution unit is used to call appropriate resources to execute the task according to resource prediction and timely monitor and dynamically adjust the resources for executing the task;

[0127] The optimization unit is used to optimize the resource prediction model according to the completion status of the task.

[0128] The present invention proposes a resource allocation method and device for an inland vessel area controller, which first establishes a resource prediction model, classifies tasks and predicts the required resources based on the resource prediction model, and then calls resources to execute tasks according to the resource prediction; it can enable tasks to be successfully completed with a minimum resource supply and meet the service quality requirements of task execution; it is conducive to the full utilization of resources.

[0129] Example 2

[0130] Embodiment 2 of the present invention provides an electronic device, including a processor, a memory and a display. It should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0131] In some embodiments, the memory may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device.

[0132] Furthermore, the memory may include both an internal storage unit of the electronic device and an external storage device. The memory is used to store application software and various data installed in the electronic device.

[0133] In some embodiments, the processor may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes stored in a memory or process data, such as the environment perception method based on point cloud data in the present invention.

[0134] In some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display is used to display information on the electronic device and to display a visual user interface. The components of the electronic device communicate with each other via a system bus.

[0135] In one embodiment, when the processor executes the resource allocation method program of the inland waterway vessel area controller in the memory, the following steps may be implemented:

[0136] Set up sonar monitoring devices with known locations in the detection waters;

[0137] The sonar monitoring device acquires the sound of water entry and records the time when the sound of water entry is acquired;

[0138] Comparison confirmed that the sound of water entry was the sound of garbage entering the water;

[0139] The location of the sound source of the garbage entering the water is determined based on the time of the sound, the distance between the sonars, and the location of the sonar monitoring device.

[0140] It should be understood that: when the processor executes the resource allocation method program of the inland vessel area controller in the memory, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0141] Furthermore, the embodiments of the present invention do not specifically limit the types of electronic devices mentioned, and the electronic devices may be portable electronic devices such as mobile phones, tablet computers, personal digital assistants (PDAs), wearable devices, and laptop computers. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as laptop computers with touch-sensitive surfaces (e.g., touch panels). It should also be understood that in some other embodiments of the present invention, the electronic device may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0142] The electronic device provided by the embodiment of the present invention is used to implement the resource allocation method of the inland vessel area controller. Therefore, the technical effects possessed by the resource allocation method of the inland vessel area controller are also possessed by the electronic device and will not be described in detail herein.

[0143] Example 3

[0144] Embodiment 3 of the present invention provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor, the resource allocation method for the inland vessel area controller provided in Embodiment 1 is implemented.

[0145] The computer storage medium provided in the embodiment of the present invention is used in the resource allocation method of the inland vessel area controller. Therefore, the technical effects possessed by the resource allocation method of the inland vessel area controller are also possessed by the computer storage medium, which will not be repeated here.

[0146] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the drawings and above. However, any equivalent changes, modifications and evolutions made by technicians familiar with the profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.

Claims

1. A resource allocation method for an inland river vessel area controller, characterized in that: The following steps are involved: Represent and describe all resources in the regional controller architecture of inland river intelligent ships and establish a resource library; Establish resource forecasting models; Classify tasks and predict required resources based on resource forecasting models; Determine whether to execute the task based on resource forecast; According to resource forecast, appropriate resources are allocated to perform the task and timely monitored, and the resources used to perform the task are dynamically adjusted; Optimize resource forecasting models based on post-task completion.

2. The resource allocation method of the inland waterway vessel area controller according to claim 1, characterized in that: Represent and describe all resources in the inland river intelligent ship regional controller architecture and establish a resource library, specifically: The resources of inland river smart ships are encoded using self-compiled uniform resource locators and encoding technology: Described using Extensible Markup Language and Resource Description Framework; Use ontology to describe the connections between resources; Build a resource library with resources that complete the description; Monitor the resource status in the resource library in real time and mark idle resources as idle.

3. The resource allocation method of the inland waterway vessel area controller according to claim 2, characterized in that: Establish a resource prediction model, specifically: Establish a historical task library with completed tasks of known types, and collect resource consumption snapshots of tasks in the historical task library; Use sparse coding to process resource snapshots, quantize them into "words", and obtain a resource dictionary; Use the resource dictionary as training data to train a linear multi-classification support vector machine SVM; A resource prediction model is established using resource dictionary and support vector machine (SVM).

4. The resource allocation method of the inland waterway vessel area controller according to claim 3, characterized in that: Classify the tasks and predict the required resources based on the resource prediction model, specifically: Classify the obtained tasks based on the resource prediction model; Determine the amount of pre-allocated resources for the task based on the resource prediction model; The performance prediction algorithm based on the task execution frequency predicts the performance index of the task under the current pre-allocated resource amount; Use binary search and control variable methods to adjust the resource supply of the task and determine the minimum resources required to complete the task successfully.

5. The resource allocation method of the inland waterway vessel area controller according to claim 4, characterized in that: The obtained tasks are classified based on the resource prediction model, specifically: Intercept a small portion of the task's input and run it as a probe: Collect resource consumption snapshots during the probe operation, process the resource snapshots with sparse coding, and quantize them into "words". Input the "word" into the SVM classifier in the resource prediction model to obtain the task category.

6. The resource allocation method of the inland waterway vessel area controller according to claim 5, characterized in that: The amount of pre-allocated resources for the task is determined based on the resource prediction model, specifically: Search the historical task library by task category, call up historical tasks of the same task category, and obtain resource consumption snapshots of historical tasks; The average resource consumption of historical tasks is obtained as the pre-allocated resource amount of the task.

7. The resource allocation method of the inland waterway vessel area controller according to claim 6, characterized in that: The performance prediction algorithm based on task execution frequency predicts the performance indicators of tasks executed under the current pre-allocated resources, specifically: Provide the input parameters and configuration parameters of the task and generate the task description function X new , X new = {detailed input information A, QoS performance requirements Q, resource consumption mode F t }, where the detailed input information A of the task includes task size, task type, etc.; Increase the value of adjacent tasks K one by one, using x n1 ;x n2 ;…;x nk represents the K neighbors of the task, d1; d2; ...; d k represents their Euler distance to the task. When the density f(k) around the new task reaches a maximum value for the first time, the K value at this time is used as the most suitable number of nearest neighbors for prediction; Calculate the contribution ψ of different neighbor tasks i , Calculate the weighted function to predict the performance of new tasks.

8. The resource allocation method of the inland waterway vessel area controller according to claim 7, characterized in that: The calculation formula of density f(k) is 9. The resource allocation method of the inland waterway vessel area controller according to claim 8, characterized in that: Contribution ψ i The calculation formula is The weighting function is 10. A resource allocation device for an inland river vessel area controller, characterized in that: include: The resource description unit is used to represent and describe all resources in the inland river intelligent ship area controller architecture and establish a resource library; A resource prediction model building unit, used for building a resource prediction model; A parsing unit, used to parse the task and predict the required resources based on the resource prediction model; A task confirmation unit, used to determine whether to execute the task according to resource prediction; The task dynamic execution unit is used to call appropriate resources to execute the task according to resource prediction and timely monitor and dynamically adjust the resources for executing the task; The optimization unit is used to optimize the resource prediction model according to the completion status of the task.