A load balancing-based server request distribution method, device and medium

Abstract

The application discloses a server request distribution method and device based on load balancing, and relates to the technical field of computer network load balancing. The method comprises the following steps: collecting network client request analysis historical traffic and request mode, obtaining traffic change trend, predicting future load according to the traffic change trend, and generating traffic distribution decision; distributing network client requests to servers according to the traffic distribution strategy, and monitoring the response time and processing capacity of each server in real time to generate server performance feedback information; judging the adjustment demand of the traffic distribution strategy based on the server performance feedback information, and generating a strategy optimization scheme; periodically reviewing the strategy optimization scheme, adjusting the load distribution parameters through a continuous learning method, and generating an optimized distribution strategy. The efficiency and stability of the overall system are improved.

Description

Technical Field

[0001] This invention relates to the field of computer network load balancing technology, and in particular to a server request distribution method, device and medium based on load balancing. Background Technology

[0002] With the rapid development of information technology and the Internet, server request traffic is constantly increasing. Load balancing has gradually become one of the core methods supporting high-concurrency and high-availability systems. Load balancing intelligently distributes client requests to different servers, thereby balancing the load on each server, avoiding overload of a single server and improving the system's processing capacity. Server request distribution methods based on load balancing have been widely used, especially in cloud computing environments and industrial Internet security control. By analyzing historical traffic and request patterns, load balancing methods can effectively predict load changes, thereby optimizing the use of server resources, improving the overall efficiency and stability of the system, and ensuring the security and reliability of the system in the industrial Internet environment.

[0003] Existing load balancing methods still have some shortcomings when dealing with complex traffic patterns and dynamic server performance. Traditional load balancing methods often rely on simple allocation algorithms, such as round-robin and least connections. These methods fail to fully consider multi-dimensional factors such as real-time server load and response time, which may result in the server load not being distributed reasonably under high concurrency. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a server request distribution method based on load balancing, which solves the problem of not being able to fully consider the real-time load and dynamic performance changes of the server.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a server request distribution method based on load balancing, comprising: collecting and analyzing historical traffic and request patterns of network client requests to obtain traffic change trends, predicting future load based on traffic change trends, and generating traffic distribution decisions; evaluating the health status and load of multiple servers based on the traffic distribution decisions, and performing server performance index analysis on the load capacity and response performance of each server to generate load assessment data; classifying each network client request by type, obtaining request attributes, combining the load assessment data with the request attributes, and generating a traffic distribution strategy through intelligent distribution; distributing network client requests to servers according to the traffic distribution strategy, and monitoring the response time and processing capacity of each server in real time to generate server performance feedback information; determining the adjustment needs of the traffic distribution strategy based on the server performance feedback information and generating a strategy optimization scheme; periodically reviewing the strategy optimization scheme and adjusting the load distribution parameters through continuous learning methods to generate an optimized distribution strategy.

[0008] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the specific steps for collecting and analyzing historical traffic and request patterns from network client requests to obtain traffic change trends are as follows:

[0009] Collect network client requests and perform traffic characteristic analysis on the network client requests using network traffic analysis methods to obtain structured datasets;

[0010] Based on the structured dataset, historical traffic is analyzed in depth to obtain traffic patterns, and the traffic patterns are grouped by time period to generate request counts;

[0011] Based on the number of requests, time-series analysis methods are used to identify patterns of traffic changes and obtain traffic trends.

[0012] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the specific steps for predicting future load based on traffic change trends and generating traffic allocation decisions are as follows:

[0013] By combining traffic change trends with historical traffic and the server's current load capacity, the future traffic load value can be estimated.

[0014] By analyzing traffic change trends using time-series analysis methods and predicting future load changes based on server status, traffic allocation decisions are generated.

[0015] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the steps of evaluating the health status and load of multiple servers according to traffic allocation decisions, and analyzing server performance indicators for the load capacity and response performance of each server to generate load assessment data are as follows:

[0016] The server health status is assessed based on traffic allocation decisions, and the server response performance under different loads is analyzed.

[0017] Evaluate the resource usage and maximum capacity of each server in response performance and generate load assessment data.

[0018] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the steps of classifying each network client request by type, obtaining request attributes, combining load assessment data with request attributes, and generating a traffic allocation strategy through intelligent distribution are as follows:

[0019] Classify and analyze the request feature data of network client requests, identify request types and access patterns, extract network protocol attributes, and assign category labels to network client requests;

[0020] Based on category tags, analyze the urgency, resource requirements, and response time requirements of network client requests, assess the priority of network client requests, and extract request attributes;

[0021] Analyze the matching degree between each request attribute and the server load capacity to generate a request allocation priority score;

[0022] Based on request allocation priority scoring, the processing capacity of each server is evaluated through an intelligent traffic distribution algorithm, and a traffic allocation strategy is formulated by combining the priority of network client requests and resource requirements.

[0023] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the steps of distributing network client requests to servers according to a traffic allocation strategy, and monitoring the response time and processing capacity of each server in real time to generate server performance feedback information are as follows.

[0024] Based on the traffic allocation strategy, each network client request is assigned to each server, and the response time and processing latency of each server are monitored in real time to generate response time monitoring data.

[0025] The processing capacity of each server is monitored in real time and combined with response time monitoring data to generate server performance feedback information.

[0026] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the specific steps for determining the adjustment requirements of the traffic allocation strategy based on server performance feedback information and generating a strategy optimization scheme are as follows:

[0027] Based on server performance feedback information, analyze the load, response latency and processing capacity of each server, identify the server with performance bottlenecks, and obtain adjustment requirements for the server with performance bottlenecks through load analysis.

[0028] Adjust the traffic allocation ratio in the traffic allocation strategy based on the adjusted demand value, and generate a strategy optimization plan.

[0029] As a preferred embodiment of the server request distribution method based on load balancing described in this invention, the steps of periodically reviewing the strategy optimization scheme and adjusting the load allocation parameters through continuous learning to generate an optimized distribution strategy are as follows:

[0030] Based on the strategy optimization plan, the latest server performance feedback data is collected regularly, and the latest server performance feedback data is compared with the traffic allocation strategy to generate a strategy review report;

[0031] Adjust the traffic allocation ratio in the strategy review report to shift the load from the bottleneck server to the server and generate an optimized strategy review report;

[0032] By analyzing the server performance bottlenecks in the post-optimization strategy review report using continuous learning methods, the traffic allocation decision was updated, and an optimized traffic splitting strategy was generated.

[0033] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the server request routing method based on load balancing as described in the first aspect of the present invention.

[0034] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the server request routing method based on load balancing as described in the first aspect of the present invention.

[0035] The beneficial effects of this invention are as follows: By collecting and analyzing historical traffic and request patterns of network client requests, requests are intelligently classified and combined with server load capacity to generate traffic allocation strategies, thereby achieving accurate traffic prediction and optimized load allocation; through intelligent traffic splitting algorithms, resource allocation can be optimized according to different request types and server status, ensuring the stability and efficiency of the system during high traffic periods; in this process, industrial internet security control mechanisms are applied to ensure the security of traffic allocation strategies and the protection of data transmission, avoiding potential security threats; continuous strategy optimization and learning mechanisms further improve system performance, avoid server overload, and ultimately achieve higher resource utilization and response speed, improving the overall system efficiency and stability. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of a server request routing method based on load balancing.

[0038] Figure 2 This is a flowchart for traffic data collection and analysis.

[0039] Figure 3 Generate a flowchart for the intelligent traffic diversion strategy.

[0040] Figure 4 Flowchart for strategy optimization closed loop. Detailed Implementation

[0041] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0042] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0044] Reference Figures 1-4 This is one embodiment of the present invention, which provides a server request splitting method based on load balancing, including the following steps:

[0045] S1. Collect and analyze historical traffic and request patterns from network client requests to obtain traffic change trends, predict future load based on traffic change trends, and generate traffic allocation decisions.

[0046] S1.1 Collect network client requests and perform traffic characteristic analysis on the network client requests using network traffic analysis methods to obtain a structured dataset.

[0047] It should be noted that metadata for each network client request is collected through logs, proxy servers, or API interfaces, including request timestamps, source IP addresses, request types, request sizes, response times, and request frequencies. This data collection captures various traffic characteristics (such as timestamps, request types, and packet sizes). Network traffic analysis methods are used to perform time-series analysis on the request data, identifying traffic trends, periodic fluctuations, and anomalies to extract valuable network behavior patterns. By comparing historical traffic with current data, traffic analysis can predict future network load and provide a basis for subsequent traffic optimization and load balancing decisions. During the analysis, requests are grouped by time periods, and the number of requests within each time period is counted. By statistically analyzing the number of requests within each time period and applying methods such as autocorrelation analysis and trend analysis, patterns in the data are discovered. Autocorrelation analysis is used to detect the correlation between adjacent time periods in the data, revealing periodic fluctuations; trend analysis helps identify long-term trends in the data, such as continuously rising or falling traffic patterns. Sudden fluctuation detection can capture abnormal changes in traffic, further helping to identify potential traffic peaks or troughs, thereby clarifying the trend of request changes. Based on different characteristics of network client requests, relevant network protocol attributes, such as TCP / UDP type and packet size, are extracted and converted into a structured format to generate a structured dataset.

[0048] It should also be noted that network traffic analysis methods, by collecting and processing metadata (such as timestamps, request types, packet sizes, etc.) from network client requests, combined with time-series analysis methods, identify traffic trends, periodic fluctuations, and anomalies. This method can reveal traffic regularities, such as traffic peaks, troughs, and sudden fluctuations, thereby predicting future network load. Through autocorrelation analysis and trend analysis, periodic changes in traffic are identified, providing data support for subsequent traffic optimization and load balancing, ensuring the rational allocation and efficient utilization of network resources.

[0049] S1.2. Based on the structured dataset, perform in-depth analysis of historical traffic to obtain traffic patterns, and group the traffic patterns by time period to generate request counts.

[0050] It should be noted that traffic information in structured datasets is filtered to ensure data accuracy and completeness. By segmenting historical traffic request timestamps, traffic data is divided into time granularities such as hours, minutes, or seconds. The number of requests within each time period quantifies the traffic volume for that period. Time-series analysis methods are used to further identify regular fluctuations, periodic changes, and outliers in the traffic, thus determining traffic patterns. For example, frequency analysis identifies peak and off-peak traffic periods and their trends across different time periods. The identified traffic patterns are grouped by time period, and the number of requests within each time period is counted to form traffic distribution data.

[0051] S1.3. Based on the number of requests, identify the changing patterns of traffic patterns and obtain traffic change trends through time series analysis.

[0052] It should be noted that detailed statistics on the number of requests within each time period are performed. Request quantity is a key quantitative indicator of traffic, reflecting network load at different times. By calculating the mean, fluctuation range, and standard deviation of the number of requests within each time period, the periodic trends and patterns of request quantity changes are identified. Autocorrelation analysis and trend analysis methods are used to further identify periodic fluctuations, seasonal trends, and sudden abnormal fluctuations in traffic, discovering patterns in traffic changes and determining peak, trough, and stable periods. The analysis process also includes identifying outliers in the data to ensure that these abnormal fluctuations are distinguished from normal fluctuations, facilitating subsequent traffic forecasting and load adjustment, and generating traffic trend data.

[0053] S1.4 Combine the traffic change trend with historical traffic and the server's current load capacity to estimate the future traffic load value.

[0054] It should be noted that a detailed review of historical traffic is conducted, and time-series analysis is used to identify patterns in traffic changes. Based on these patterns, future traffic is predicted to determine the potential number of requests within a given future timeframe. The predicted traffic trends are then compared with historical traffic data to analyze their correlation and identify the temporal relationship between traffic changes and historical data. This, combined with the server's current load capacity (including processing power, memory usage, CPU load, network bandwidth, etc.), is used to assess the current server load level. Finally, by combining the traffic trends with the server's current load capacity, future load values ​​are estimated.

[0055] S1.5 Analyze traffic change trends using time-series analysis methods, predict future load changes based on server status, and generate traffic allocation decisions.

[0056] It should be noted that historical traffic data undergoes preprocessing to remove outliers and fill in missing data, ensuring data integrity and accuracy. Modeling of the historical traffic data identifies periodic changes, trend fluctuations, and sudden fluctuations. This analysis reveals patterns in traffic changes and captures the characteristics of traffic fluctuations across different time periods. Regression analysis is used to combine the trends in historical traffic data with server status data (such as CPU utilization, memory usage, and network bandwidth) to analyze past traffic change patterns. This includes autocorrelation analysis, regression analysis, ARIMA models, and LSTM neural networks to identify periodic fluctuations, trend changes, and sudden events in traffic. Considering the current state of the server, predicted values ​​for future load changes are generated. These predictions help anticipate load fluctuations, providing a basis for traffic allocation decisions and ensuring resources are adjusted appropriately according to expected load. Based on the predicted future load changes, traffic allocation decisions are generated.

[0057] It should also be noted that traffic allocation decisions are based on historical traffic analysis and server performance evaluation results, combined with the priority of network client requests, resource requirements, and server load capacity. Traffic allocation decisions use intelligent algorithms to rationally distribute network requests to the most suitable servers to optimize resource utilization and improve response efficiency. It considers the real-time status and load of servers, ensuring that high-priority requests are processed first and balancing the load of each server during periods of high traffic, thereby achieving efficient traffic management.

[0058] S2. Evaluate the health status and load of multiple servers based on traffic allocation decisions, and perform server performance index analysis on the load capacity and response performance of each server to generate load assessment data.

[0059] S2.1 Evaluate the resource usage and maximum capacity of each server in the response performance assessment to generate load assessment data.

[0060] It should be noted that real-time status data of the server is collected, including indicators such as CPU utilization, memory usage, disk I / O, and network bandwidth. By comparing the real-time monitoring data with the server's maximum load capacity, it is analyzed whether the server is overloaded, whether there is response time latency or resource bottlenecks, and the response time, processing capacity, and data throughput of each server under different loads are calculated to evaluate the server's working efficiency under actual load conditions.

[0061] It should also be noted that load assessment data is a dataset generated by monitoring and analyzing server resource usage (such as CPU utilization, memory usage, disk I / O, and network bandwidth) to evaluate the performance of each server under different load conditions. By comparing the server's current load with its maximum capacity, load assessment data can help identify whether the server is overloaded and provide a basis for traffic allocation decisions, thereby optimizing the allocation of server resources.

[0062] S2.2 Based on the server performance evaluation report, assess the resource usage and maximum carrying capacity of each server, and generate load evaluation data.

[0063] It should be noted that the resource usage data in the server performance evaluation report is used to analyze the resource consumption of each server under different load conditions. A comparative analysis method of resource utilization and performance is employed, comparing the server's maximum available resources with the current resource usage to determine whether the server is under critical load or close to overload. Combined with historical performance data and load test results, the maximum number of requests or tasks that each server can handle under different loads is assessed, generating load evaluation data.

[0064] It should also be noted that under different load conditions, including light load, medium load, high load, burst load, and sustained high load, the server's resource consumption (such as CPU, memory, disk I / O, and network bandwidth) will vary differently under each condition.

[0065] S3. Classify each network client request by type, obtain request attributes, combine load assessment data with request attributes, and generate traffic allocation strategies through intelligent traffic splitting.

[0066] It should be noted that existing methods treat all network client requests as the same type and distribute traffic using simple load balancing algorithms (such as round-robin or least connections). These methods often do not consider specific request attributes, such as request type or priority, and only distribute traffic based on traffic load and server load status, making it impossible to optimize for different types of requests.

[0067] This invention categorizes each network client request by type, obtains the specific attributes of the request, and combines these attributes with load assessment data to employ an intelligent traffic allocation strategy. This method can more accurately optimize traffic allocation based on request characteristics (such as urgency, resource requirements, etc.), thereby improving efficiency and responsiveness.

[0068] S3.1 Classify and analyze the request feature data of network client requests, identify request types and access patterns, extract network protocol attributes, and assign category labels to network client requests.

[0069] It should be noted that extracting various characteristics from network client requests provides the data foundation for classification analysis. Classifying and analyzing these network client request characteristic data identifies different request types and access patterns. By analyzing these characteristics, different types of network client requests can be distinguished, such as GET requests, POST requests, static resource requests, and dynamic requests. Access patterns, such as periodic access, bursty access, and persistent access, also need to be identified. This information helps understand the characteristics of different request types and their resource requirements. Protocol attributes further aid in understanding the network behavior of network client requests. Based on the analysis results of request types and access patterns, a category label is assigned to each network client request.

[0070] It should also be noted that request characteristic data refers to various types of information extracted from network client requests, including request timestamps, request source IPs, request types (such as GET, POST), request sizes, response times, and request frequencies. This characteristic data helps analyze request behavior patterns, such as periodic or bursty access, and can be used to assess request priority and resource requirements. By analyzing request characteristics, traffic allocation strategies can be optimized to achieve efficient processing of different types of requests.

[0071] S3.2 Analyze the urgency, resource requirements, and response time requirements of network client requests based on category labels, assess the priority of network client requests, and extract request attributes.

[0072] It should be noted that network client requests are categorized into different classes based on their category tags. For example, network client requests can be divided into high-priority requests, low-priority requests, and regular requests. The urgency of network client requests is assessed based on the characteristics of each category tag, determined by factors such as the time sensitivity of the request and whether it is a real-time task. Resource requirements, such as CPU, memory, and bandwidth demands, are analyzed based on the category tag of each network client request to assess the resource consumption level of each request. A response time cap is set to determine whether a network client request needs to be prioritized. For example, real-time requests may require lower response times, while non-real-time requests are processed later. These analysis results allow for the assignment of a priority score to each network client request and the extraction of specific request attributes.

[0073] S3.3 Analyze the matching degree between each request attribute and the server load capacity, and generate a request allocation priority score.

[0074] It should be noted that by comparing the relevant attributes of network client requests (such as request type, priority, resource requirements, etc.) with the server's load capacity (such as CPU utilization, memory usage, network bandwidth, etc.), the efficiency of each network client request can be assessed under the current server load. For example, if a network client request requires high CPU and memory resources, but the server's CPU utilization is nearing full capacity, the priority of the network client request may need to be adjusted. The comparison results help determine which network client requests are efficiently processed on the current server and which require reassignment. For requests requiring high resources, it is necessary to ensure that the server has sufficient load capacity to handle them. If the server's load capacity is low, the priority of the network client request should be appropriately reduced. Based on the server's response performance (such as response time, throughput, etc.), assess whether the network client request can be processed within the specified time. High-priority network client requests must be preferentially assigned to servers with strong response capabilities and light load. By combining the matching of the resource requirements of network client requests with the server's load capacity, a request allocation priority score is calculated, expressed as:

[0075] ;

[0076] in, Rate the priority; This refers to the resource requirements requested by the network client. The resource requirements are determined by analyzing various attributes of the network client's request and the current load status of the server. The weight is assigned to network client requests based on factors such as the urgency, priority, and time sensitivity of the requests, and is obtained through request category tags and business requirement definitions. This refers to the server's load capacity, which is determined by monitoring the server's hardware resources and current load status. This represents the server's current load, which is obtained by monitoring the server's resource usage in real time. This refers to the server's response performance, which is obtained by monitoring the time it takes for the server to process requests, including request response time and processing latency.

[0077] Converting resource requirements, load capacity, current load, and response performance into proportional values ​​relative to their maximum values ​​ensures that each variable becomes a dimensionless value, allowing them to be calculated and compared on the same scale.

[0078] S3.4. Based on request allocation priority scoring, the processing capacity of each server is evaluated through intelligent traffic splitting algorithm, and traffic allocation strategy is formulated in combination with the priority of network client requests and resource requirements.

[0079] It should be noted that each server is comprehensively evaluated based on the priority and resource requirements of each network client request, combined with the server's load capacity (such as CPU utilization, memory usage, network bandwidth, and response time). By comparing the processing power of each server with the resource requirements of the network client requests, the intelligent traffic allocation algorithm will assign a suitable server to each network client request. For high-priority network client requests, they are preferentially assigned to servers with lighter loads and stronger processing capabilities, while for low-priority network client requests, they are assigned to servers with heavier loads, but it must be ensured that the server's maximum capacity is not exceeded, thus formulating a traffic allocation strategy.

[0080] It should also be noted that the intelligent traffic distribution algorithm matches requests with server load capacity by analyzing the attributes of network client requests in real time, such as request type, priority, resource requirements, and response time requirements. For example, based on the urgency of the request, the intelligent traffic distribution algorithm prioritizes allocating high-priority requests to servers with fast response times and light loads; low-priority requests can be allocated to servers with heavier loads. The algorithm comprehensively considers the real-time load status and resource usage of the servers, dynamically adjusting traffic allocation to ensure optimized resource utilization and avoid server overload.

[0081] Traffic allocation strategies utilize intelligent algorithms to rationally distribute network requests across various servers based on the characteristics of client requests, server load capacity, and priorities. These strategies consider server current load, response capabilities, request urgency, and resource requirements to optimize resource utilization and improve response efficiency. By dynamically adjusting allocation ratios, high-priority requests are processed first, while simultaneously balancing the load across servers, thus enhancing overall performance and stability.

[0082] S4. Distribute network client requests to servers according to the traffic allocation strategy, and monitor the response time and processing capacity of each server in real time to generate server performance feedback information.

[0083] S4.1. Based on the traffic allocation strategy, each network client request is allocated to each server, and the response time and processing latency of each server are monitored in real time to generate response time monitoring data.

[0084] It should be noted that, based on the performance and resource usage of each server, and according to the priority and resource requirements of network client requests, each network client request is intelligently allocated to the corresponding server. Once the allocation is complete, the response time and processing latency of each server need to be monitored in real time to ensure that each network client request is processed within the specified time. By setting up monitoring tools, the response time of each server (the time interval from receiving a network client request to starting to respond) and the processing latency (the time interval from starting to completing processing) are continuously tracked, generating response time monitoring data.

[0085] S4.2. Monitor the processing capacity of each server in real time and combine it with response time monitoring data to generate server performance feedback information.

[0086] It should be noted that performance data for each server is continuously tracked. This data is collected in real-time using dedicated monitoring tools to ensure a real-time understanding of each server's load status. By comparing and analyzing the processing capacity and response time data of each server, we can assess whether the server can maintain good processing performance under the current load. For example, when CPU utilization is close to full load, it may lead to increased response time. Therefore, it is necessary to pay attention to these potential performance bottlenecks and generate server performance feedback information.

[0087] It should also be noted that server performance feedback information refers to data on server resource usage obtained through real-time monitoring, including metrics such as CPU utilization, memory usage, disk I / O, network bandwidth, response time, and processing latency. This information helps assess the server's current load status and processing capacity, promptly identify performance bottlenecks, and provide a basis for traffic allocation decisions, ensuring that the system can operate efficiently and stably when the load changes.

[0088] S5. Based on server performance feedback information, determine the need to adjust the traffic allocation strategy and generate a strategy optimization plan.

[0089] S5.1 Based on server performance feedback information, analyze the load, response latency and processing capacity of each server, identify the server with performance bottlenecks, and obtain adjustment requirements for the server with performance bottlenecks through load analysis.

[0090] It should be noted that the CPU utilization, memory usage, network bandwidth, and disk I / O metrics for each server are extracted from server performance feedback information, and these metrics are monitored in real time. The response latency of each server (the time required from receiving a network client request to returning a response) and the server's processing capacity (including data processing speed and network client request processing capacity) are used to identify performance bottlenecks by comparing the performance data of each server. Performance bottlenecks typically manifest as excessively long response latency or resource utilization approaching full capacity. Load analysis assesses the gap between the server's load capacity and the current load to determine the resource allocation ratio that needs adjustment to optimize server performance and generate adjustment requirements.

[0091] S5.2 Adjust the traffic allocation ratio in the traffic allocation strategy according to the adjusted demand value, and generate a strategy optimization plan.

[0092] It should be noted that by comparing the adjusted demand values ​​with the resource usage of each server, it's possible to identify which servers need increased traffic allocation and which need decreased traffic allocation. For example, if a server's load is nearing its limit, the network client request traffic allocated to that server needs to be reduced; if a server's load is low, the traffic it processes needs to handle needs to be increased. Adjusting the traffic allocation ratio in the traffic allocation strategy ensures reasonable resource utilization and load balancing. For each adjustment to the traffic allocation ratio, the server's maximum capacity, response time, and the priority requirements of network client requests need to be considered to ensure that high-priority network client requests receive a fast response, thus generating a strategy optimization plan.

[0093] S6. Regularly review the strategy optimization plan and adjust the load distribution parameters through continuous learning methods to generate optimized traffic splitting strategies.

[0094] It should be noted that existing methods rely on static load balancing strategies and periodic manual or pre-set reviews and adjustments. These methods generally modify traffic allocation according to fixed rules, lacking adaptability and learning capabilities to real-time changes. Therefore, they may not be able to effectively cope with system changes when dealing with dynamic loads and bursts of traffic.

[0095] This invention automatically adjusts load allocation parameters through continuous learning, ensuring that the strategy can be dynamically optimized based on real-time server performance feedback and traffic changes. Periodic reviews not only consider historical data but also use adaptive algorithms to learn and adjust the strategy in real time, improving adaptability and optimization effectiveness, and effectively avoiding performance bottlenecks caused by static strategies.

[0096] S6.1. Regularly collect the latest server performance feedback data according to the strategy optimization plan, compare the latest server performance feedback data with the traffic allocation strategy, and generate a strategy review report.

[0097] It should be noted that a regular data collection interval (e.g., hourly or daily) should be set, and the latest performance feedback data for each server should be automatically collected using monitoring tools. The current load of each server should be matched against the traffic allocation ratio in the traffic distribution strategy to assess whether there is uneven traffic distribution or excessive server load. This comparison allows us to determine whether the current traffic allocation strategy performs as expected in actual operation, generating a strategy review report.

[0098] S6.2 Adjust the traffic allocation ratio in the strategy review report to transfer the load of the bottleneck server to the server and generate an optimized strategy review report.

[0099] It should be noted that the bottleneck servers identified in the strategy review report are used to assess their load and responsiveness. The traffic allocation ratio for the bottleneck servers is adjusted, shifting some load to high-performing servers. High-performing servers typically exhibit low load, fast response times, and high processing power. By analyzing the resource status and load capacity of these high-performing servers, it is determined that they can receive more traffic without performance degradation. The traffic allocation ratio is adjusted, allocating more traffic to high-performing servers while reducing the traffic allocated to bottleneck servers, generating an optimized strategy review report.

[0100] S6.3. Analyze the server performance bottlenecks in the strategy review report through continuous learning methods, update traffic allocation decisions, and generate optimized traffic splitting strategies.

[0101] It should be noted that the continuous learning method analyzes the changing trends of each server by comparing the performance feedback data in the optimized strategy review report, identifying servers with resource constraints or response delays. These performance bottlenecks typically manifest as insufficient processing power. Based on these analysis results, traffic allocation decisions are updated, adjusting the traffic allocation ratio to divert more traffic to servers with stronger processing power, reducing the traffic burden on bottleneck servers. The updated traffic allocation decisions are then used to generate an optimized traffic distribution strategy.

[0102] This embodiment also provides a computer device applicable to a server request splitting method based on load balancing, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the server request splitting method based on load balancing as proposed in the above embodiment.

[0103] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0104] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the server request distribution method based on load balancing as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0105] In summary, this invention achieves accurate traffic prediction and optimized load distribution by: collecting and analyzing historical traffic and request patterns from network clients, intelligently classifying requests, and combining this with server load capacity to generate traffic allocation strategies; optimizing resource allocation based on different request types and server status through intelligent traffic splitting algorithms, ensuring system stability and efficiency during high-traffic periods; applying industrial internet security control mechanisms to ensure the security of traffic allocation strategies and data transmission protection, avoiding potential security threats; and continuously optimizing strategies and learning mechanisms further improve system performance, prevent server overload, and ultimately achieve higher resource utilization and response speed, enhancing the overall system efficiency and stability.

[0106] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A server request distribution method based on load balancing, characterized in that: include, Collect and analyze historical traffic and request patterns from network client requests to obtain traffic change trends, predict future load based on traffic change trends, and generate traffic allocation decisions. The health status and load of multiple servers are assessed based on traffic allocation decisions, and server performance indicators are analyzed for the load capacity and response performance of each server to generate load assessment data. Each network client request is categorized by type, request attributes are obtained, load assessment data is combined with request attributes, and a traffic allocation strategy is generated through intelligent traffic splitting. Network client requests are allocated to servers according to the traffic allocation strategy, and the response time and processing capacity of each server are monitored in real time to generate server performance feedback information. Based on server performance feedback information, determine the need to adjust the traffic allocation strategy and generate a strategy optimization plan; Regularly review the strategy optimization plan and adjust the load distribution parameters through continuous learning methods to generate optimized traffic splitting strategies.

2. The server request distribution method based on load balancing as described in claim 1, characterized in that: The process of collecting and analyzing historical traffic and request patterns from network clients to obtain traffic change trends involves the following steps: Collect network client requests and perform traffic characteristic analysis on the network client requests using network traffic analysis methods to obtain structured datasets; Based on the structured dataset, historical traffic is analyzed in depth to obtain traffic patterns, and the traffic patterns are grouped by time period to generate request counts; Based on the number of requests, time-series analysis methods are used to identify patterns of traffic changes and obtain traffic trends.

3. The server request distribution method based on load balancing as described in claim 2, characterized in that: The specific steps for predicting future load based on traffic change trends and generating traffic allocation decisions are as follows. By combining traffic change trends with historical traffic and the server's current load capacity, the future traffic load value can be estimated. By analyzing traffic change trends using time-series analysis methods and predicting future load changes based on server status, traffic allocation decisions are generated.

4. The server request distribution method based on load balancing as described in claim 3, characterized in that: The process involves assessing the health and load of multiple servers based on traffic allocation decisions, analyzing server performance metrics for each server's load capacity and response performance, and generating load assessment data. The specific steps are as follows: The server health status is assessed based on traffic allocation decisions, and the server response performance under different loads is analyzed. Evaluate the resource usage and maximum capacity of each server in response performance and generate load assessment data.

5. The server request distribution method based on load balancing as described in claim 4, characterized in that: The specific steps for classifying each network client request by type, obtaining request attributes, combining load assessment data with request attributes, and generating a traffic allocation strategy through intelligent traffic splitting are as follows. Classify and analyze the request feature data of network client requests, identify request types and access patterns, extract network protocol attributes, and assign category labels to network client requests; Based on category tags, analyze the urgency, resource requirements, and response time requirements of network client requests, assess the priority of network client requests, and extract request attributes; Analyze the matching degree between each request attribute and the server load capacity to generate a request allocation priority score; Based on request allocation priority scoring, the processing capacity of each server is evaluated through an intelligent traffic distribution algorithm, and a traffic allocation strategy is formulated by combining the priority of network client requests and resource requirements.

6. The server request distribution method based on load balancing as described in claim 5, characterized in that: The steps for allocating network client requests to servers according to the traffic allocation strategy, and for monitoring the response time and processing capacity of each server in real time to generate server performance feedback information are as follows: Based on the traffic allocation strategy, each network client request is assigned to each server, and the response time and processing latency of each server are monitored in real time to generate response time monitoring data. The processing capacity of each server is monitored in real time and combined with response time monitoring data to generate server performance feedback information.

7. The server request distribution method based on load balancing as described in claim 6, characterized in that: The steps for determining the need to adjust the traffic allocation strategy based on server performance feedback information and generating a strategy optimization plan are as follows: Based on server performance feedback information, analyze the load, response latency and processing capacity of each server, identify the server with performance bottlenecks, and obtain adjustment requirements for the server with performance bottlenecks through load analysis. Adjust the traffic allocation ratio in the traffic allocation strategy based on the adjusted demand value, and generate a strategy optimization plan.

8. The server request distribution method based on load balancing as described in claim 7, characterized in that: The process involves periodically reviewing the strategy optimization plan and adjusting load allocation parameters through continuous learning to generate an optimized traffic distribution strategy. The specific steps are as follows: Based on the strategy optimization plan, the latest server performance feedback data is collected regularly, and the latest server performance feedback data is compared with the traffic allocation strategy to generate a strategy review report; Adjust the traffic allocation ratio in the strategy review report to shift the load from the bottleneck server to the server and generate an optimized strategy review report; By analyzing the server performance bottlenecks in the post-optimization strategy review report using continuous learning methods, the traffic allocation decision was updated, and an optimized traffic splitting strategy was generated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the server request splitting method based on load balancing as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the server request routing method based on load balancing as described in any one of claims 1 to 8.

Images