Forecasting platform automatic deployment and load balancing control method and system

Abstract

The invention discloses a forecasting platform automatic deployment and load balancing control method, system, device, medium and program, and belongs to the technical field of forecasting management and control. The method comprises the following steps: acquiring original multi-target data of a forecasting platform, and preprocessing the original multi-target data to obtain multi-target data of the forecasting platform; performing optimization processing by adopting an NSGA-II algorithm model according to the multi-target data of the forecasting platform to generate an optimal deployment scheme; generating a configuration file according to the optimal deployment scheme, sending the configuration file to a server in the forecasting platform, checking the server receiving the configuration file, and generating a load distribution scheme; and monitoring the load condition of the server in real time according to the load distribution scheme, and dynamically adjusting the task distribution quantity of the server according to the load condition. According to the method, multiple conflicting targets are comprehensively considered, the optimal decision of forecasting platform deployment and load distribution is realized, platform deployment is quickly and accurately completed according to the optimal decision, and dynamic adjustment task distribution is completed in real time.

Description

Technical Field

[0001] This invention relates to the field of forecasting and control technology, specifically to a method, system, device, medium, and program for automated deployment and load balancing control of a forecasting platform. Background Technology

[0002] Forecasting platforms not only need to integrate high-resolution observational data, advanced numerical forecasting models, and powerful data analysis capabilities, but also must possess the ability to respond quickly and adjust flexibly to cope with complex and ever-changing natural environments. This trend has directly driven a dramatic increase in the scale and complexity of forecasting platforms, evolving from small systems with a single server to large distributed clusters containing thousands or even tens of thousands of servers, covering multiple stages such as data collection, processing, analysis, and forecast dissemination.

[0003] However, traditional forecasting platform deployment and management largely rely on manual operation, which is not only inefficient but also prone to errors. In the early stages of platform construction, from hardware preparation and software installation to system configuration, each step requires meticulous operation by professionals. This process is time-consuming and prone to configuration errors, affecting subsequent system stability and operational efficiency. Even more challenging is the exponential increase in complexity of daily operation and maintenance management as the platform scales up, including system updates, troubleshooting, and performance monitoring. Human resources alone cannot provide comprehensive coverage and timely responses. Furthermore, the significant differences in forecast workload across different time periods pose a substantial challenge to system resource allocation. For example, during typhoon season or peak marine activity, the surge in forecast tasks, if not effectively allocated to achieve load balancing, can lead to server overload. This not only reduces forecast speed but may also affect the accuracy and timeliness of forecast results due to delayed processing, ultimately negatively impacting socio-economic activities. Summary of the Invention

[0004] To address the shortcomings of existing meteorological and marine forecasting platforms, which heavily rely on manual processes for deployment, management, resource allocation, and load balancing, resulting in low efficiency, error-proneness, and difficulty in handling large-scale, highly complex, and fluctuating workloads, this invention provides an automated deployment and load balancing control method for forecasting platforms. This method comprehensively considers multiple conflicting objectives to achieve optimal decisions in forecasting platform deployment and load allocation. Based on these optimal decisions, the platform can be deployed quickly and accurately, and task allocation can be dynamically adjusted in real time.

[0005] To achieve the above objectives, the present invention provides the following technical solution.

[0006] In a first aspect, the present invention provides a method for automated deployment and load balancing control of a forecasting platform, comprising: The raw multi-target data of the forecasting platform is collected and preprocessed to obtain the multi-target data of the forecasting platform. Based on multi-target data from the forecasting platform, the NSGA-II algorithm model is used for optimization to generate the optimal deployment plan. A configuration file is generated based on the optimal deployment scheme and sent to the server in the forecast platform. The server that receives the configuration file is then checked, and a load distribution scheme is generated after the check passes. The server load is monitored in real time according to the load distribution scheme, and the task allocation of the server is dynamically adjusted according to the load to obtain the operating status of the forecasting platform. Determine if the current forecasting platform's operational status triggers a warning; if so, regenerate the optimal deployment plan.

[0007] As a further improvement of the present invention, the raw multi-target data of the forecasting platform is collected and preprocessed to obtain multi-target data of the forecasting platform, including: The system collects hardware resource information and memory usage of the servers in the forecasting platform; characteristics of forecasting tasks and execution status of historical forecasting tasks, such as response time and accuracy, to form the raw multi-objective data of the forecasting platform. Data cleaning and missing value imputation were performed on the raw multi-target data of the forecast platform to obtain the multi-target data of the forecast platform.

[0008] As a further improvement of the present invention, the step of optimizing the multi-target data from the forecasting platform using the NSGA-II algorithm model to generate the optimal deployment scheme includes: Based on multi-objective data from the forecasting platform, the degree of load difference between servers is measured to obtain the load imbalance, response time, and resource utilization of the forecasting platform. Based on the load imbalance, response time, and resource utilization of the forecasting platform, a deployment and load allocation scheme for the forecasting platform is generated. The NSGA-II algorithm model is used to find the optimal deployment scheme among the deployment and load distribution schemes of the forecast platform.

[0009] As a further improvement of the present invention, the step of generating a configuration file according to the optimal deployment scheme and sending the configuration file to the server in the forecasting platform, followed by checking the server receiving the configuration file, and generating a load distribution scheme after the check passes, includes: Generate a configuration file based on the optimal deployment plan, including the server's IP address, port number, and database connection information; Send the generated configuration file to the server, confirm that the server receiving the configuration file has started normally and is in a ready state, and then perform a smoke test. The server that passes the smoke test is marked as a successfully configured server. Generate a load distribution plan based on the load of the successfully configured server.

[0010] As a further improvement of the present invention, the step of monitoring the server's load in real time according to the load allocation scheme, and dynamically adjusting the server's task allocation according to the load to obtain the operating status of the forecasting platform includes: Monitor the server load in real time according to the load distribution scheme and collect real-time server load information; A task allocation plan is generated based on the real-time load of the server, and tasks are allocated to the corresponding servers according to the task allocation plan. If the server is overloaded, some tasks will be migrated to servers with lower load. The load balancing effect of the forecasting platform will be evaluated at set time intervals to obtain the operating status of the forecasting platform.

[0011] As a further improvement of the present invention, the step of determining whether the current forecasting platform's operating status triggers a warning, and if so, regenerating the optimal deployment plan, includes: Based on the operational status of the forecasting platform, determine whether the current forecasting platform has triggered a warning, including: The current CPU utilization rate of the forecasting platform exceeds 85%, and the forecasting platform is deviating from its historical state; If a warning is triggered, the optimal deployment plan will be regenerated. If not triggered, it will continue to operate according to the current operating status of the forecasting platform.

[0012] Secondly, the present invention provides an automated deployment and load balancing control system for a forecasting platform, comprising: Data processing module: used to collect raw multi-target data from the forecasting platform and perform preprocessing to obtain multi-target data from the forecasting platform; The optimal solution module is used to optimize the deployment plan based on multi-target data from the forecasting platform using the NSGA-II algorithm model. Load balancing scheme: This is used to generate a configuration file based on the optimal deployment scheme and send the configuration file to the server in the forecasting platform. Then, the server that receives the configuration file checks it, and if the check passes, a load balancing scheme is generated. Platform Status Module: Used to monitor the server load in real time according to the load distribution scheme, dynamically adjust the server task allocation according to the load, and obtain the predicted platform operating status. Warning Detection Module: Used to determine whether the current forecasting platform's operating status has triggered a warning. If so, the optimal deployment plan is regenerated.

[0013] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned method for automated deployment and load balancing control of a forecasting platform.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for automated deployment and load balancing control of a forecasting platform.

[0015] Fifthly, the present invention provides a computer program product, including computer instructions, which, when executed by a processor, implement the aforementioned method for automated deployment and load balancing control of a forecasting platform.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This method automates the entire process, from the acquisition and preprocessing of raw multi-target data to generating the optimal deployment scheme using the NSGA-II algorithm model, and then generating configuration files based on the scheme and accurately sending them to the server. This improves deployment efficiency, ensures accuracy and completeness, and effectively avoids various problems that may arise from manual operation. Secondly, this method generates a load distribution scheme based on the optimized deployment scheme, accurately allocating resources to each server to achieve efficient resource utilization, avoiding resource idleness or over-occupancy, and improving the overall resource utilization of the forecasting platform. Furthermore, it monitors server load in real time and dynamically adjusts task allocation based on the load. When a server load is too high, its task allocation is automatically reduced to prevent server failure due to overload; when the load is low, the task allocation is appropriately increased to fully utilize the server's performance potential. This dynamic adjustment mechanism ensures that the forecasting platform is always in optimal operating condition. Attached Figure Description

[0017] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way. In the drawings: Figure 1 This is a flowchart illustrating an automated deployment and load balancing control method for a forecasting platform according to the present invention. Figure 2 This is a schematic diagram of the structure of an automated deployment and load balancing control system for a forecasting platform according to the present invention; Figure 3 This is a schematic diagram of an electronic device in an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] To address the shortcomings of existing meteorological and marine forecasting platforms, which heavily rely on manual processes for deployment, management, resource allocation, and load balancing, resulting in low efficiency, error-proneness, and difficulty in handling large-scale, highly complex, and fluctuating workloads, this invention provides an automated deployment and load balancing control method for forecasting platforms. Figure 1 As shown, the method includes: S100: Collect raw multi-target data from the forecasting platform and preprocess it to obtain multi-target data from the forecasting platform; S200: Based on multi-target data from the forecasting platform, the NSGA-II algorithm model is used for optimization to generate the optimal deployment plan; S300: Generates a configuration file based on the optimal deployment scheme and sends the configuration file to the server in the forecast platform. Then, it checks the server that received the configuration file. If the check passes, it generates a load distribution scheme. S400: Monitors the server load in real time according to the load distribution scheme, dynamically adjusts the server task allocation according to the load, and obtains the operating status of the forecast platform. S500: Determines whether the current forecasting platform's operating status triggers a warning; if so, it regenerates the optimal deployment plan.

[0021] This method comprehensively considers multiple conflicting objectives to achieve optimal decision-making on forecast platform deployment and load allocation. Based on the optimal decision, the platform deployment is completed quickly and accurately, and task allocation is dynamically adjusted in real time.

[0022] The present invention will be further explained below with reference to specific implementation schemes.

[0023] A method for automated deployment and load balancing control of a forecasting platform, comprising: S1: Collect various types of data related to the forecasting platform, including server hardware resource information such as CPU utilization, memory usage, disk I / O, network bandwidth, forecasting task characteristics such as task type, data volume, computational complexity, and historical forecasting task execution such as response time and accuracy, to form the raw multi-objective data of the forecasting platform.

[0024] The original multi-target data of the forecasting platform is cleaned by adding missing values ​​and removing outliers to obtain the multi-target data of the forecasting platform.

[0025] S2: Based on the multi-objective data obtained from the forecasting platform, the NSGA-II algorithm is used for multi-objective optimization.

[0026] The objective functions include minimizing server load imbalance, minimizing forecast task response time, and maximizing server resource utilization.

[0027] If task j is assigned to server i, then Otherwise, it is 0. If server i is activated and put into use, then Otherwise, it is 0.

[0028] Based on the multi-target data acquired from the forecasting platform, the degree of load difference between servers is measured using the following formula:

[0029] in, To minimize load imbalance; n is the number of servers, It is the load of the i-th server. This is the average load across all servers.

[0030]

[0031] in, For response time; Number of tasks; It is a task Response time; response time The average time from submission to completion of a forecasting task can be determined by collecting historical forecasting task execution data, statistically analyzing the response time of each task, and then taking the average as the current system's response time metric. Minimizing this objective ensures that forecasting tasks can be processed and responded to quickly.

[0032]

[0033] In the formula, CPU utilization of server i; This represents the memory utilization rate of server i. CPU weight; Memory weight. Resource utilization. This is the sum of resource utilization across all servers. Resource utilization can be a comprehensive indicator of CPU utilization, memory utilization, etc. A weighted average is used to calculate a comprehensive resource utilization index. Maximizing this objective ensures that server resources are fully utilized. Response time is the average time required from submitting a forecast task to its completion. Response time is primarily affected by the following factors: task allocation strategy; server load; and network transmission latency.

[0034] To minimize response time, the response time of each task is statistically analyzed based on historical forecast task execution data, and its average value is calculated. The goal is to reduce task processing latency by optimizing task scheduling and resource allocation. A shorter response time indicates that forecast tasks can be processed and responded to more quickly.

[0035] Resource utilization reflects the overall usage of resources on a server (such as CPU, memory, disk I / O, etc.). To maximize resource utilization, a weighted average method can be used to calculate the overall resource utilization of all servers:

[0036] in, The weight of each resource represents the importance of different resources; Let i be the resource utilization rate of the i-th server; To maximize the utilization of resources.

[0037] Based on the forecasting platform's load imbalance, response time, and resource utilization, a set of initial solutions is randomly generated. Each solution represents a deployment and load allocation scheme for the forecasting platform. Each solution includes information such as server selection and task allocation. Each individual in the population is non-dominated and ranked, into different levels, with lower levels indicating better performance. Within the same level, the crowding distance is calculated for each individual to distinguish similar individuals and ensure population diversity. New populations are generated through selection, crossover, and mutation operations, and the process iteratively optimizes until a termination condition is met.

[0038] Specifically, the NSGA-II algorithm first decodes each individual in the population, calculating its three target values ​​(f1, f2, f3) according to a predefined objective function to quantify the performance of the deployment scheme. Then, based on these target values, it performs a non-dominated sort, dividing the entire population into multiple levels of fronts. The first front contains all non-dominated Pareto optimal solutions, ensuring the search direction moves towards the truly excellent solution space. To maintain population diversity, within the same non-dominated front, the NSGA-II algorithm calculates the crowding distance of each individual, prioritizing those located in sparse regions of the solution space with higher crowding, thus effectively avoiding getting trapped in local optima. During the selection process, a binary tournament strategy is used, randomly selecting two individuals and prioritizing those with higher non-dominated rankings; if the rankings are the same, it favors individuals with higher crowding, thus achieving "selecting the best from the worst."

[0039] The selected individuals are evolved through crossover and mutation operations: crossover exchanges some task allocation relationships between parent individuals with a high probability, combining their superior characteristics; mutation randomly changes the task allocation target of offspring individuals with a low probability, introducing new search possibilities. After each generation of optimization, the algorithm implements an elite retention strategy, merging the parent and offspring populations, re-sorting and recalculating non-dominated populations, and retaining only the top N optimal individuals to form the next generation population, thus ensuring that excellent solutions are not lost. When the number of iterations reaches the preset maximum number of generations, the algorithm terminates and outputs all solutions on the first non-dominated front, forming an optimal solution set. Based on the optimal solution set, an optimal deployment scheme is formed that makes different trade-offs among the three objectives of load balancing, response time, and resource utilization.

[0040] S3: Generate the corresponding configuration file based on the optimal deployment plan, including the server's IP address, port number, database connection information, etc., and deploy it to the corresponding server. Then, perform automated health checks by calling health check endpoints on the server or checking the status of critical processes to confirm that the server has started normally and is in a ready state. Execute a set of simple smoke tests, such as verifying whether the database connection is smooth and whether the computing service can receive tasks, to ensure that the core functions are available. Only when the health checks of all components pass is the automated deployment marked as "server successfully configured".

[0041] Start the successfully configured server of the forecasting platform to ensure the normal operation of the system, and generate a load distribution plan based on the load of the successfully configured server.

[0042] S4: Based on the load balancing scheme, monitor server load in real time and dynamically adjust task allocation. Collect server load information in real time, such as CPU utilization and memory usage. Generate a task allocation scheme based on the real-time server load and assign predicted tasks to appropriate servers. If a server is overloaded, migrate some tasks to servers with lower load. Regularly evaluate the load balancing effect and adjust the load balancing strategy according to the actual situation to ensure system performance and stability.

[0043] S5: Continuously monitor the operational status of the forecasting platform, including server hardware resource usage, forecasting task execution, and system response time.

[0044] Set to Warning or Critical. A warning will be triggered when CPU usage exceeds 85%, and a critical warning will be triggered when it exceeds 95%.

[0045] For certain indicators with obvious periodic patterns, a dynamic baseline algorithm based on machine learning is used to determine whether the forecasting platform deviates from its historical state. If it deviates, an alarm can be triggered even if the CPU utilization rate does not exceed 85%.

[0046] When disk I / O increases abnormally, the system can check whether there are a large number of data write tasks in the same period, which helps to quickly locate the root cause.

[0047] If a warning is triggered, the optimal deployment plan will be regenerated based on S2; otherwise, operation will continue based on the current operating status of the forecasting platform. The second objective of this invention is to propose an automated deployment and load balancing control system for a forecasting platform, such as... Figure 2 As shown, it includes: Data processing module 100: used to collect raw multi-target data from the forecasting platform and perform preprocessing to obtain multi-target data from the forecasting platform; Optimal Solution Module 200: This module is used to optimize multi-target data from the forecasting platform using the NSGA-II algorithm model to generate the optimal deployment plan. Load balancing scheme 300: This scheme generates a configuration file based on the optimal deployment scheme and sends the configuration file to the server in the forecasting platform. Then, it checks the server that received the configuration file and generates a load balancing scheme after the check is passed. Platform Status Module 400: Used to monitor the server load in real time according to the load distribution scheme, dynamically adjust the server task allocation according to the load, and obtain the predicted platform operating status. Warning Module 500: Used to determine whether the current operating status of the forecasting platform has triggered a warning. If so, the optimal deployment plan will be regenerated.

[0048] like Figure 3 As shown, a third objective of this invention is to provide an electronic device comprising a processor 601, a memory 602, and a display screen 603. The memory 602 and the display screen 603 are both connected to the processor 601, such as via a bus 604. Optionally, the electronic device may further include a transceiver 605. It should be noted that in practical applications, the transceiver 605 is not limited to one type, and the structure of this electronic device does not constitute a limitation on the embodiments of this application.

[0049] Processor 601 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 601 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0050] Bus 604 may include a pathway for transmitting information between the aforementioned components. Bus 604 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 604 can be divided into address bus, data bus, control bus, etc.

[0051] The memory 602 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0052] The memory 602 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 601. The processor 601 is used to execute the application code stored in the memory 602 to implement the content shown in the foregoing method embodiments.

[0053] Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0054] A fourth objective of this invention is to provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the aforementioned functions. Figure 1 The illustrated method embodiments include various processes. For example, a memory may include instructions that can be executed by a processor of an electronic device to perform the described method.

[0055] A computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), staging random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0056] A fifth objective of this invention is to provide a computer program product comprising computer instructions that, when executed by a processor, implement the above-described... Figure 1 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0057] Many embodiments and applications beyond the examples provided will be apparent to those skilled in the art upon reading the foregoing description. Therefore, the scope of this teaching should not be determined by reference to the foregoing description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

[0058] The above content provides a further detailed description of the present invention. It should not be construed that the specific embodiments of the present invention are limited to this. For those skilled in the art, several simple deductions or substitutions can be made without departing from the concept of the present invention, and all such deductions or substitutions should be considered to fall within the scope of protection of the present invention as defined by the submitted claims.

Claims

1. A method for automated deployment and load balancing control of a forecasting platform, characterized in that, include: The raw multi-target data of the forecasting platform is collected and preprocessed to obtain the multi-target data of the forecasting platform. Based on multi-target data from the forecasting platform, the NSGA-II algorithm model is used for optimization to generate the optimal deployment plan. A configuration file is generated based on the optimal deployment scheme and sent to the server in the forecast platform. The server that receives the configuration file is then checked, and a load distribution scheme is generated after the check passes. The server load is monitored in real time according to the load distribution scheme, and the task allocation of the server is dynamically adjusted according to the load to obtain the operating status of the forecasting platform. Determine if the current forecasting platform's operational status triggers a warning; if so, regenerate the optimal deployment plan.

2. The method for automated deployment and load balancing control of a forecasting platform according to claim 1, characterized in that, The raw multi-target data of the forecasting platform is collected and preprocessed to obtain the multi-target data of the forecasting platform, including: The system collects hardware resource information and memory usage of the servers in the forecasting platform; characteristics of forecasting tasks and execution status of historical forecasting tasks, such as response time and accuracy, to form the raw multi-objective data of the forecasting platform. Data cleaning and missing value imputation were performed on the raw multi-target data of the forecast platform to obtain the multi-target data of the forecast platform.

3. The method for automated deployment and load balancing control of a forecasting platform according to claim 1, characterized in that, The process involves optimizing multi-target data from the forecasting platform using the NSGA-II algorithm model to generate the optimal deployment scheme, including: Based on multi-objective data from the forecasting platform, the degree of load difference between servers is measured to obtain the load imbalance, response time, and resource utilization of the forecasting platform. Based on the load imbalance, response time, and resource utilization of the forecasting platform, a deployment and load allocation scheme for the forecasting platform is generated. The NSGA-II algorithm model is used to find the optimal deployment scheme among the deployment and load distribution schemes of the forecast platform.

4. The method for automated deployment and load balancing control of a forecasting platform according to claim 1, characterized in that, The process involves generating a configuration file based on the optimal deployment scheme and sending it to the server in the forecasting platform. The server receiving the configuration file then checks it; if the check passes, a load distribution scheme is generated, including: Generate a configuration file based on the optimal deployment plan, including the server's IP address, port number, and database connection information; Send the generated configuration file to the server, confirm that the server receiving the configuration file has started normally and is in a ready state, and then perform a smoke test. The server that passes the smoke test is marked as a successfully configured server. Generate a load distribution plan based on the load of the successfully configured server.

5. The method for automated deployment and load balancing control of a forecasting platform according to claim 1, characterized in that, The process of monitoring the server load in real time according to the load distribution scheme, dynamically adjusting the server's task allocation based on the load, and obtaining the forecast platform's operating status includes: Monitor the server load in real time according to the load distribution scheme and collect real-time server load information; A task allocation plan is generated based on the real-time load of the server, and tasks are allocated to the corresponding servers according to the task allocation plan. If the server is overloaded, some tasks will be migrated to servers with lower load. The load balancing effect of the forecasting platform will be evaluated at set time intervals to obtain the operating status of the forecasting platform.

6. The method for automated deployment and load balancing control of a forecasting platform according to claim 1, characterized in that, The step of determining whether the current forecasting platform's operating status has triggered a warning, and if so, regenerating the optimal deployment plan, includes: Based on the operational status of the forecasting platform, determine whether the current forecasting platform has triggered a warning, including: The current CPU utilization rate of the forecasting platform exceeds 85%, and the forecasting platform is deviating from its historical state; If a warning is triggered, the optimal deployment plan will be regenerated. If not triggered, it will continue to operate according to the current operating status of the forecasting platform.

7. An automated deployment and load balancing control system for a forecasting platform, characterized in that, include: Data processing module: used to collect raw multi-target data from the forecasting platform and perform preprocessing to obtain multi-target data from the forecasting platform; The optimal solution module is used to optimize the deployment plan based on multi-target data from the forecasting platform using the NSGA-II algorithm model. Load balancing scheme: This is used to generate a configuration file based on the optimal deployment scheme and send the configuration file to the server in the forecasting platform. Then, the server that receives the configuration file checks it, and if the check passes, a load balancing scheme is generated. Platform Status Module: Used to monitor the server load in real time according to the load distribution scheme, dynamically adjust the server task allocation according to the load, and obtain the predicted platform operating status. Warning Detection Module: Used to determine whether the current forecasting platform's operating status has triggered a warning. If so, the optimal deployment plan is regenerated.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the automated deployment and load balancing control method for a forecasting platform as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for automated deployment and load balancing control of a forecasting platform as described in any one of claims 1-6.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the automated deployment and load balancing control method for a forecasting platform as described in any one of claims 1-6.

Images