Shunting processing method and system, program product and readable storage medium
By analyzing historical load data and predicting loads, and dynamically adjusting resource allocation in combination with business priorities, the problem of unbalanced resource utilization in the intelligent computing center is solved, and more efficient network traffic management and system stability are achieved.
Patent Information
- Application Number
- CN202411211536.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-30
AI Technical Summary
In the intelligent computing center, the static allocation method is difficult to adapt to complex and changing network environments, resulting in unbalanced resource utilization and the inability to effectively manage dynamic and burst network traffic.
By obtaining historical service load data for each port, analyzing common traffic patterns and peak time periods, predicting load data, and calculating business priorities based on business type, processing scale and urgency, dynamically adjusting resource allocation to ensure that important and emergency services are obtained Priority is given.
The rational allocation of resources is achieved, the balance of resource utilization in the intelligent computing center is improved, and the system can adjust resource allocation in a timely manner during actual operation, avoid performance degradation or resource waste caused by load deviation, and maintain stable operation of the system.
Smart Images

Figure CN118945115A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of traffic diversion, and in particular to a traffic diversion processing method, system, program product and readable storage medium. Background Art
[0002] As an emerging high-performance computing facility, network traffic management has become a key link in ensuring the network performance and service quality of the intelligent computing center. Among many network devices, the diversion processing system is an important part of network traffic management, and its performance directly affects the operating efficiency and user experience of the entire network. In related technologies, a static allocation method can be used, that is, network traffic is allocated to different processing units according to preset rules.
[0003] However, this static allocation method often performs poorly in the face of complex and changing network environments. Due to the dynamic and sudden nature of network traffic, fixed allocation rules are difficult to adapt to real-time changing network conditions, resulting in unbalanced resource utilization within the intelligent computing center. Summary of the invention
[0004] The present application provides a diversion processing method, system, program product and readable storage medium for improving the balance of resource utilization in an intelligent computing center.
[0005] In a first aspect, the present application provides a diversion processing method, which is applied to a diversion processing system, the method comprising: obtaining historical business load data of each port, and analyzing the historical load data based on a pattern recognition algorithm to obtain a common traffic pattern and a peak time period; predicting the business load data within a preset time period based on the common traffic pattern and the peak time period to obtain a predicted load data collection, wherein the predicted load data collection contains the predicted load data of each of the ports; obtaining business type information, processing scale information and urgency information of the current business in each port, and calculating the business priority of all the current businesses based on the business type information, the processing scale information and the urgency information to obtain a business priority collection; allocating processing resources to each port based on the predicted load data collection and the business priority collection, and allocating input business traffic based on the processing resources and business priorities.
[0006] By adopting the above technical solution, we first obtain the historical business load data of each port and analyze it to obtain the common traffic patterns and peak time periods. Then, based on this information, we predict the business load within the preset time period to obtain a collection of predicted load data. Then, we obtain the business type, processing scale and urgency information to calculate the business priority collection, so that important and urgent businesses can be given priority. Based on the predicted load data collection and the business priority collection, we allocate processing resources and business traffic, thereby achieving reasonable allocation of resources and improving the balance of resource utilization in the intelligent computing center.
[0007] In combination with some embodiments of the first aspect, in some embodiments, the step of predicting the business load data within a preset time period based on the common traffic pattern and the peak time period specifically includes: classifying the common traffic pattern to obtain a plurality of traffic pattern types; setting a corresponding prediction model for each of the traffic pattern types, wherein different types of traffic patterns correspond to different prediction models; dividing the preset time period into a plurality of time units, and determining the traffic pattern type to which each of the time units belongs; selecting a corresponding prediction model according to the traffic pattern type to which each of the time units belongs; inputting historical data for the same period into the selected prediction model to obtain predicted load data for each of the time units; and merging the predicted load data to obtain a collection of predicted load data within the preset time period.
[0008] By adopting the above technical solution, common traffic patterns are classified and different prediction models are set, which can more accurately predict different traffic patterns. The preset time period is divided into multiple time units and the type of traffic pattern is determined. After selecting the corresponding prediction model, the historical data of the same period is input to obtain the predicted load data, and finally the collection is merged to make the prediction result more accurate, avoid the waste of resources and unreasonable allocation, and improve the system's adaptability to different traffic patterns.
[0009] In combination with some embodiments of the first aspect, in some embodiments, the step of calculating the business priority of all the current businesses based on the business type information, the processing scale information and the urgency information specifically includes: classifying the business type information, dividing the business types into first business, second business and third business, and assigning different weight coefficients to each of them; calculating the resource consumption index of each business based on the processing scale information, and the resource consumption index is proportional to the processing scale; setting the time sensitivity coefficient based on the urgency information; multiplying the weight coefficient, the resource consumption index and the time sensitivity coefficient to obtain a priority score; and sorting all the current businesses according to the priority score to obtain a collection of business priorities.
[0010] By adopting the above technical solution, the business types are classified and assigned different weight coefficients, which reflects the difference in importance of different business types. The resource consumption index is calculated based on the processing scale information, so that resource allocation takes into account the actual needs of the business more reasonably, and the time sensitivity coefficient is set to reflect the urgency. The weight coefficient, resource consumption index and time sensitivity coefficient are multiplied together to obtain the priority score and sorted to obtain the business priority set, which can ensure that important, urgent and resource-intensive businesses are processed first, improving the responsiveness and processing efficiency of the intelligent computing center to different businesses.
[0011] In combination with some embodiments of the first aspect, in some embodiments, after the step of allocating processing resources to each port based on the predicted load data collection and the business priority collection, the method also includes: receiving multiple user-defined custom data models, each of the custom data models including a regular expression and a corresponding processing strategy; associating each of the custom data models with one or more of the ports, so that each port is responsible for processing business traffic that matches a specific custom data model; parsing the input business traffic data and extracting data features; matching the data features with the regular expressions of each of the custom data models to obtain a first data model; when the match is successful, allocating the successfully matched business traffic data to the corresponding port according to the processing strategy corresponding to the first data model and the business priority collection.
[0012] By adopting the above technical solution, a user-defined custom data model is received, which includes regular expressions and processing strategies, so that the system can distribute traffic according to the specific needs of the user, associate the custom data model with the port, and let each port be responsible for processing specific matching business traffic. The input business traffic data is parsed and features are extracted. After matching with the regular expression, the successfully matched business traffic is distributed to the corresponding port according to the processing strategy and business priority set, thereby meeting the needs of different users for specific business traffic processing.
[0013] In combination with some embodiments of the first aspect, in some embodiments, after the step of allocating the successfully matched business traffic data to the corresponding port according to the processing strategy corresponding to the first data model and the business priority set, the method also includes: real-time monitoring of the actual load data of each port, and comparing it with the predicted load data; when it is detected that the deviation between the actual load data of any port and the predicted load exceeds a preset threshold, dynamically adjusting the resource allocation and business traffic allocation ratio between ports according to the actual load data of each port, the predicted load data and the business priority, and adjusting them to within a preset load balancing threshold, where the preset load balancing threshold is the maximum allowable deviation percentage between the actual load data of each port and its predicted load data.
[0014] By adopting the above technical solution, the actual load data of each port is monitored in real time and compared with the predicted load data. When the deviation between the actual load and the predicted load exceeds the preset threshold, the resource allocation and business traffic allocation ratio between ports are dynamically adjusted according to the actual load data, predicted load data and business priority, ensuring that the system can adjust resource allocation in time according to actual conditions in actual operation, avoiding system performance degradation or resource waste caused by excessive load deviation. Through dynamic adjustment, the intelligent computing center always maintains a relatively stable operating state, ensuring the smooth operation of the business.
[0015] In combination with some embodiments of the first aspect, in some embodiments, after the step of allocating processing resources to each port based on the predicted load data collection and the service priority collection, the method also includes: detecting the operating status of all ports, and if a first port is in a faulty state, obtaining the first service flow information of the first port, the first service flow information including the service type, service data and the service priority of all the service data; analyzing the current load status and remaining processing capacity of other target ports, the other target ports being ports operating normally other than the first port; and reallocating the first service flow of the first port to the other target ports one by one in the order of the service priority from high to low based on a dynamic load balancing algorithm.
[0016] By adopting the above technical solution, the operating status of all ports is detected. When a port is found to be in a faulty state, the service flow information of the port is obtained, the current load status and remaining processing capacity of other normally operating ports are analyzed, and the service flow of the faulty port is reallocated to other target ports in the order of service priority from high to low based on the dynamic load balancing algorithm, thus avoiding service interruption caused by a single port failure. At the same time, allocation according to service priority ensures that important services can be processed first, improving the fault tolerance and overall stability of the system.
[0017] In combination with some embodiments of the first aspect, in some embodiments, after the step of redistributing the business traffic of the first port to the other normally operating ports one by one in the order of the business priority from high to low based on the dynamic load balancing algorithm, the method also includes: calculating the new load level of each of the other target ports in real time; if the new load level of the first target port exceeds the preset load balancing threshold, storing the first business traffic in the priority queue; and distributing the business traffic in the priority queue according to preset time intervals.
[0018] By adopting the above technical solution, after the service traffic of the faulty port is redistributed to other normal operating ports based on the dynamic load balancing algorithm, the new load level of each other target port is calculated in real time. If the new load level of a target port exceeds the preset load balancing threshold, the corresponding service traffic is stored in the priority queue, and the service traffic in the priority queue is distributed according to the preset time interval. Real-time calculation of the new load level can timely grasp the load changes of each port and ensure the stability of the system after the service traffic is redistributed.
[0019] In a second aspect, an embodiment of the present application provides a diversion processing system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the diversion processing system to perform the method described in the first aspect and any possible implementation method of the first aspect.
[0020] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when the computer program product is run on a diversion processing system, enables the diversion processing system to execute the method described in the first aspect and any possible implementation of the first aspect.
[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a diversion processing system, the diversion processing system executes the method described in the first aspect and any possible implementation method of the first aspect.
[0022] It can be understood that the flow separation processing system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.
[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application obtains the historical business load data of each port and analyzes it to obtain the common traffic patterns and peak time periods, which helps to understand the traffic patterns of the port. Then, based on this information, the business load within the preset time period is predicted to obtain a collection of predicted load data. Then, the business type, processing scale and urgency information are obtained to calculate a collection of business priorities, so that important and urgent businesses can be given priority. Processing resources and business traffic are allocated based on the collection of predicted load data and the collection of business priorities, thereby achieving reasonable allocation of resources.
[0024] 2. This application receives user-defined custom data models, including regular expressions and processing strategies, so that the system can distribute traffic according to the specific needs of users, associate the custom data model with the port, and make each port responsible for processing specific matching business traffic. The input business traffic data is parsed and features are extracted. After matching with the regular expression, the successfully matched business traffic is distributed to the corresponding port according to the processing strategy and business priority set, so as to meet the needs of different users for specific business traffic processing.
[0025] 3. This application monitors the actual load data of each port in real time and compares it with the predicted load data. When the deviation between the actual load and the predicted load exceeds the preset threshold, the resource allocation and business traffic allocation ratio between ports are dynamically adjusted according to the actual load data, predicted load data and business priority, ensuring that the system can adjust resource allocation in time according to actual conditions during actual operation, avoiding system performance degradation or resource waste due to excessive load deviation. Through dynamic adjustment, the intelligent computing center always maintains a relatively stable operating state, ensuring the smooth progress of business. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a flow chart of the diversion processing method in the embodiment of the present application; Figure 2 is another flow chart of the diversion processing method in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the diversion processing system in an embodiment of the present application. DETAILED DESCRIPTION
[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.
[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.
[0029] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the diversion processing method in an embodiment of the present application.
[0030] S101 . Obtain historical service load data of each port, and analyze the historical load data based on a pattern recognition algorithm to obtain a common traffic pattern and a peak time period.
[0031] Among them, port refers to the interface used for data transmission on network equipment; historical business load data refers to the business traffic data processed by each port in the past period of time; pattern recognition algorithm is used to identify specific patterns or regularities from large amounts of data; common traffic patterns refer to traffic change patterns that frequently appear in historical data; peak time period refers to the time interval when the traffic reaches its peak.
[0032] Specifically, the system first collects historical service load data from each port within a certain time range (such as the past three months). This data includes information such as the traffic size and service type distribution at each time point. Then, the system uses pre-set pattern recognition algorithms (such as cluster analysis, time series analysis, etc.) to identify frequently occurring traffic change patterns, such as daytime peaks on weekdays and lows on weekends, which are called common traffic patterns. At the same time, the system can also determine the time period when the traffic reaches its peak, that is, the peak time period.
[0033] In some embodiments, the acquisition and analysis process of the historical business load data can be implemented in a variety of ways: Optionally, the system sets a data collection module to regularly collect traffic data from each port and store the data in a dedicated database. Then, the historical data of each port is modeled using a time series analysis method, such as an autoregressive integrated moving average model (ARIMA), to identify periodic patterns and abnormal peaks. Finally, similar traffic patterns are grouped by a clustering algorithm (such as K-means) to obtain common traffic patterns, and the peak time period is determined by setting a threshold; Optionally, the system can use a machine learning method, such as a long short-term memory network (LSTM), to directly learn the original historical load data. The LSTM model can capture long-term and short-term time dependencies and automatically extract common traffic patterns. At the same time, a peak detection algorithm, such as a sliding window method, is set to identify peak points in historical data, thereby determining the peak time period. It is understandable that other data analysis and machine learning methods can also be used to implement the analysis and pattern recognition of historical load data, which is not limited here.
[0034] It is understandable that the diversion processing system also supports link layer, VLAN, MPLS, IP, TCP, UDP, SCTP, ICMP, IP layer tunnel, L2TP tunnel, IPsec (AH, ESP encapsulation) tunnel message recognition when performing historical business load analysis, and supports the mixed input of control plane signaling data and user plane business data of mobile core networks such as GPRS, WCDMA, TD-CDMA, LTE, etc., which can enhance the system's ability to identify different types of network traffic.
[0035] S102: predicting the service load data within a preset time period based on the common traffic pattern and the peak time period to obtain a predicted load data collection, wherein the predicted load data collection includes the predicted load data of each of the ports.
[0036] The predicted load data refers to the estimated value of the business load at a certain point in the future.
[0037] Specifically, the system first determines the time range that needs to be predicted, that is, the preset time period. Then, based on the common traffic patterns and peak time period information obtained in the previous step, the prediction process considers the periodic patterns, peak characteristics, and possible seasonal changes in historical data. For each port, the predicted load data is generated at each time point (such as every hour or every 15 minutes) within the preset time period, and finally the prediction results of all ports are summarized to form a complete set of predicted load data.
[0038] In some embodiments, the prediction process can be implemented in a variety of ways: Optionally, the system can use time series prediction methods, such as ARIMA models or exponential smoothing methods. First, select appropriate model parameters based on common traffic patterns. Then, input historical data into the model to generate prediction values for future time points. For known peak time periods, peak adjustment factors can be additionally applied to improve prediction accuracy. Finally, the prediction results of each port are integrated into a collection of predicted load data; Optionally, the system can use machine learning methods, such as recurrent neural networks (RNN) or Prophet models, and use historical data, common traffic patterns, and peak time period information as input features during training. After the model training is completed, the time information of the preset time period is input to obtain the predicted load data for each port. It can be understood that other prediction algorithms or multi-model integration methods can also be used to achieve load prediction, which is not limited here.
[0039] It can be understood that the diversion processing system can also support flow management functions, can transfer the first N packets of each flow, support flow statistics, packet sampling, and message header output functions, and can more accurately predict and manage various types of business traffic.
[0040] S103, obtaining the service type information, processing scale information and urgency information of the current service in each port, and calculating the service priorities of all the current services according to the service type information, the processing scale information and the urgency information to obtain a service priority set.
[0041] Among them, the business type information indicates the category to which the current business belongs, such as data transmission, video streaming, web browsing, etc.; the processing scale information refers to the amount of resources required for the business, including the amount of data, computational complexity, etc.; the urgency information is used to indicate the time sensitivity of the business, such as the level of real-time requirements; the business priority refers to the ranking of business importance based on a comprehensive evaluation of multiple factors.
[0042] Specifically, this step is executed when the system receives a new service request or regularly updates the service status. The system first obtains the service information currently being processed from each port, including the service type, processing scale, and urgency. For the service type, the system predefines some categories, such as critical services, ordinary services, and low-priority services. The processing scale information can be determined by analyzing the data volume of the service, the required computing resources, etc. The urgency is evaluated based on factors such as the deadline of the service and the user level. After obtaining this information, the priority of each service is calculated using a preset algorithm or rule. For example, for certain types of services, urgency is more important than processing scale. Finally, all calculated service priorities are aggregated to form a service priority set.
[0043] In some embodiments, the calculation of business priorities and the generation of a collection can be achieved in a variety of ways: Optionally, the system can adopt a multi-factor weighted scoring method. First, set weight coefficients for business type, processing scale, and urgency respectively. Then, quantify each factor, such as converting the business type into a numerical score, normalizing the processing scale to a value between 0-1, and converting the urgency into a time sensitivity score. These scores are multiplied by the corresponding weights and summed to obtain a comprehensive priority score for each business. All businesses are sorted according to these scores to generate a collection of business priorities; Optionally, the system can use machine learning methods, such as decision trees or random forest algorithms, to collect historical business data and their actual priorities as training sets, and use business types, processing scales, and urgency as features to train a model that can predict business priorities. After the model training is completed, the relevant information of the current business is input to obtain the predicted priority, and the predicted results of all businesses are sorted to form a collection of business priorities. It can be understood that other algorithms or hybrid methods can also be used to achieve the calculation and sorting of business priorities, which are not limited here.
[0044] S104: Allocate processing resources to each port based on the predicted load data set and the service priority set, and allocate input service traffic based on the processing resources and service priorities.
[0045] Among them, processing resources refer to the computing, storage, network bandwidth and other resources that the system can use to process business; resource allocation refers to allocating appropriate processing capacity to each port based on predicted load and business priority; business traffic allocation refers to distributing input business requests to different ports for processing.
[0046] Specifically, firstly, based on the predicted load data collection, the expected load of each port in the future period is evaluated, and the information in the service priority collection is considered to ensure that high-priority services can obtain sufficient resources. The resource allocation algorithm (such as dynamic programming or heuristic algorithm) is used to allocate appropriate processing resources to each port, where processing resources include adjusting CPU time slices, memory allocation, network bandwidth and other parameters. After the resource allocation is completed, the newly entered service traffic is dynamically allocated according to the allocation results and the real-time service priority. High-priority services may be allocated to ports with lighter loads or more sufficient resources.
[0047] In some embodiments, resource allocation and service traffic allocation can be achieved in a variety of ways: Optionally, the system can adopt a rule-based hierarchical allocation strategy. According to the predicted load data, the total system resources are initially allocated to each port in proportion, considering the service priority, and a certain proportion of resources are reserved for high-priority services. Then, a dynamic threshold adjustment mechanism is used to dynamically adjust resource allocation based on real-time monitoring of port loads. Finally, for newly incoming service traffic, the system selects the most suitable port for allocation based on its priority and the actual load status of each port at present; Optionally, the system can use machine learning methods such as reinforcement learning algorithms. First, the current state of the system (including predicted load, service priority, real-time load, etc.) is used as the environmental state. Then, the resource allocation and traffic allocation operations are defined as action spaces. Next, a reward function is designed, taking into account factors such as the overall system throughput and the processing efficiency of high-priority services. Through continuous interaction and learning with the environment, it can be understood that other optimization algorithms or hybrid methods can also be used to achieve intelligent allocation of resources and traffic, which is not limited here.
[0048] It can be understood that the diversion processing system can also access, process and forward high-speed data, support business functions such as message identification, rule matching, data processing, traffic balancing, same-source and same-destination, convergence and diversion, flow management, flow statistics, packet sampling, message header output, etc., and has functions such as five-tuple filtering, feature code filtering, compound rule filtering, protocol and application filtering, etc.
[0049] The diversion processing system also supports HTTP diversion functions, including the ability to divert special fields of single-packet and cross-packet HTTP messages, supports domain name diversion functions, can divert specific domain names, supports application diversion functions, can directly output or discard business traffic according to application protocols and application types, and supports GTP-C, GTP-U association and output functions.
[0050] The diversion processing system also supports message header stripping, which can strip the outer IP, VLAN, VXLAN or MPLS header, supports the carrying of output message information, and can modify the source and destination MAC addresses of the link layer header of the output message to identify the relevant information of the output message, and supports the processing of unidentified messages.
[0051] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the diversion processing method in an embodiment of the present application.
[0052] S201, obtaining historical service load data of each port, and analyzing the historical load data based on a pattern recognition algorithm to obtain a common traffic pattern and peak time period; It can be understood that this step is similar to step S101 and will not be described in detail here.
[0053] S202: predicting the service load data within a preset time period based on the common traffic pattern and the peak time period to obtain a predicted load data collection, wherein the predicted load data collection includes predicted load data for each of the ports; This step specifically includes: The common traffic pattern is classified to obtain multiple traffic pattern types; In this step, the traffic diversion system first conducts an in-depth analysis of historical traffic data and uses clustering algorithms (such as K-means or hierarchical clustering) to identify different traffic patterns. The system considers multiple features, including traffic size, volatility, duration, and periodicity. For example, the system can identify the following types of traffic patterns: (1) Regular weekday pattern: Monday to Friday, 9 a.m. to 6 p.m., with large and stable traffic; (2) Weekday peak pattern: Weekdays from 9 a.m. to 11 a.m. and 2 p.m. to 4 p.m., with a sharp increase in traffic; (3) Nighttime trough pattern: Daily traffic from 1 a.m. to 5 a.m. is significantly reduced; (4) Weekend leisure pattern: Saturday and Sunday, traffic is moderate and relatively evenly distributed; (5) Holiday burst pattern: During specific holidays, traffic presents irregular and sudden increases. The system also considers the impact of seasonal changes and special events (such as large online events) on traffic patterns to ensure the comprehensiveness and accuracy of classification.
[0054] A corresponding prediction model is set for each type of traffic pattern, wherein different types of traffic patterns correspond to different prediction models; In this step, the traffic diversion processing system selects and configures the most suitable prediction model for each identified traffic pattern type. For the regular weekday pattern, the system uses the ARIMA (autoregressive integrated moving average) model, which can effectively capture the trend and seasonality of time series data. The weekday peak pattern uses the Prophet model, which is a time series prediction model developed by Facebook and is suitable for processing data with multiple periodicities and holiday effects. The nighttime trough pattern uses a simple exponential smoothing method because this pattern is relatively stable and does not require a complex model. The weekend leisure mode uses the random forest algorithm, which can handle nonlinear relationships and complex interaction effects. For the holiday burst pattern, the system selects the long short-term memory network (LSTM), which can learn long-term dependencies to handle irregular burst events.
[0055] Dividing the preset time period into a plurality of time units, and determining a flow pattern type to which each of the time units belongs; In this step, the preset time period is divided into multiple time units, and the traffic pattern type to which each time unit belongs is determined: the traffic diversion processing system divides the preset time period (such as a week) into multiple smaller time units, usually in hours. The system first creates a time series data structure, each element represents an hour, a total of 168 elements (7 days × 24 hours). Then, the system traverses each time unit and determines the type of traffic pattern to which it belongs by analyzing historical data and current situations. This process involves multiple steps: calculating statistical features such as the average flow, standard deviation, and peak ratio of each time unit, comparing the extracted features with the predefined traffic pattern type, using indicators such as Euclidean distance or cosine similarity to measure the degree of matching, considering the surrounding environment of the time unit, such as the pattern type of the previous and next time periods, to ensure the consistency of the classification, querying the predefined special event calendar (such as holidays, promotions), and specially marking the affected time units, continuously monitoring real-time traffic data, and adjusting the pattern type of the time unit in real time if significant deviations are detected.
[0056] According to the traffic pattern type to which each time unit belongs, a corresponding prediction model is selected; In this step, the traffic diversion processing system selects the most appropriate prediction model for each time unit based on the traffic pattern type of each time unit determined in the previous step. The system maintains a model mapping table that associates traffic pattern types with corresponding prediction models. The selection process is as follows: the system queries the model mapping table, finds the corresponding prediction model based on the traffic pattern type of the time unit, creates an instance of the selected model, and loads the pre-trained model parameters. The model parameters are fine-tuned according to the specific characteristics of the time unit (such as the date, cycle position, etc.) to improve the prediction accuracy, and the selected model is quickly verified using recent historical data to ensure that its performance meets expectations.
[0057] Input the historical data of the same period into the selected forecasting model to obtain the forecast load data for each time unit; In this step, the diversion processing system prepares the corresponding historical contemporaneous data for each time unit and inputs it into the selected forecast model. The preparation process of historical contemporaneous data includes: extracting the contemporaneous data of the past few weeks or months corresponding to the current forecast time unit from the database, removing outliers and missing values, using interpolation or mean filling methods to handle missing data, creating additional features such as lagged values, moving averages, etc., and standardizing or normalizing the data. For each time unit, the system performs the following steps: warming up the model with part of the historical data, and using the rolling forecast method to gradually forecast forward to obtain the forecast load data.
[0058] The predicted load data are merged to obtain a set of predicted load data within the preset time period.
[0059] In this step, the predicted load data is merged to obtain a set of predicted load data within the preset time period. The diversion processing system merges the predicted load data of each time unit obtained in the previous step to form a complete set of predicted load data within the preset time period.
[0060] S203, obtaining the service type information, processing scale information and urgency information of the current service in each port, and calculating the service priority of all the current services according to the service type information, the processing scale information and the urgency information to obtain a service priority set; This step specifically includes: Classifying the service type information, dividing the service type into a first service, a second service and a third service, and assigning different weight coefficients to each of them; In this step, the traffic diversion processing system first classifies the service type information, divides the service into the first, second and third services, and assigns different weight coefficients. The system maintains a service type database, which contains predefined service types and their default classifications. When a new service enters the system, the system automatically matches its type and classifies it. For example, financial transaction services are classified as the first service and assigned a weight coefficient of 1.5; video streaming services are classified as the second service and assigned a weight coefficient of 1.2; and ordinary web browsing is classified as the third service and assigned a weight coefficient of 1.0.
[0061] Calculate the resource consumption index of each business according to the processing scale information, where the resource consumption index is proportional to the processing scale; In this step, next, the system calculates the resource consumption index of each business based on the processing scale information. The system first defines a benchmark unit, such as the resource consumption of processing 1MB of data per second. Then, the system evaluates the actual processing scale of each business and converts it into a multiple of the benchmark unit. For example, if a video streaming business needs to process 10MB of data per second, its resource consumption index is 10. The system uses a linear mapping function to convert the processing scale into the resource consumption index to ensure that the resource consumption index is proportional to the processing scale. In addition, the system also considers the characteristics of different types of businesses, such as CPU-intensive or I / O-intensive, and makes appropriate adjustments to the resource consumption index.
[0062] Setting a time sensitivity coefficient based on the urgency information; In this step, the system then sets the time sensitivity coefficient based on the urgency information. The system defines a time sensitivity scale ranging from 1 to 10, where 1 represents time-insensitive services and 10 represents extremely time-sensitive services. The system determines the urgency of each service by analyzing the characteristics of the service and the parameters set by the user. For example, real-time video conferencing is assigned a time sensitivity coefficient of 9, while background data backup is assigned a coefficient of 2. The system also implements a dynamic adjustment mechanism that can adjust the time sensitivity coefficient based on the real-time performance of the service and user feedback. For example, if a delay in a video conference is detected, the system will automatically increase its time sensitivity coefficient.
[0063] The weight coefficient, the resource consumption index and the time sensitivity coefficient are multiplied to obtain a priority score; In this step, the system multiplies the weight coefficient, resource consumption index, and time sensitivity coefficient to obtain the priority score. The priority score calculation formula is: priority score = weight coefficient × resource consumption index × time sensitivity coefficient. For example, a first-class service (weight coefficient 1.5), a resource consumption index of 8, and a time sensitivity coefficient of 7 has a priority score of 1.5 × 8 × 7 = 84. The priority score also includes the upper and lower limits of the priority to prevent some services from obtaining too high or too low priority due to extreme values.
[0064] All current services are sorted according to the priority scores to obtain a service priority set.
[0065] In this step, finally, the system sorts all current services according to the priority scores to obtain a collection of service priorities. The system uses a quick sort algorithm to sort the priority scores of all services in descending order. After the sorting is completed, the system generates an ordered list of all service IDs and their corresponding priority scores, namely the collection of service priorities. The system also implements a segmentation processing mechanism to divide services with similar priorities into different priority groups, such as a high priority group (score 80-100), a medium priority group (score 50-79), and a low priority group (score 0-49).
[0066] S204: Allocate processing resources to each port based on the predicted load data set and the service priority set, and allocate input service traffic based on the processing resources and service priorities.
[0067] In this step, the system first reads the predicted load data collection to determine the expected load of each port in the future time period. The system uses time series prediction algorithms, such as ARIMA (autoregressive integrated moving average model), to predict the load of each port every hour in the next 24 hours. Then, the system reads the service priority collection, sorts the services from high to low priority, and uses a weighted polling algorithm to allocate processing resources to each port. Assume that the system has 4 ports and a total CPU resource of 100 units. Based on the predicted load, the system can allocate CPU resources as follows: 40 units are allocated to port 1 (forecast load 80%), 30 units are allocated to port 2 (forecast load 60%), and 15 units are allocated to port 3 and port 4 (both forecast loads 40%).
[0068] S205, receiving multiple user-defined data models, each of which includes a regular expression and a corresponding processing strategy; A custom data model is a user-defined data processing rule that identifies a specific type of data flow and specifies how to process it. A regular expression is an expression that matches a specific pattern string, and is used here to identify a specific type of data packet or traffic. A processing policy specifies the processing method that should be taken after matching data.
[0069] The system provides a graphical web interface for users to create custom data models. Users need to enter the following information: Model name: Give the model a descriptive name, such as "Financial Transaction Model" or "Video Streaming Model", Regular expression: Used to match specific data patterns. For example, "^TRADE_[AZ]{3}_\d{6}$" can be used to match all strings starting with TRADE_ followed by 3 uppercase letters and 6 numbers, which represents a specific format of financial transaction data.
[0070] Users can choose from a list of predefined policies, such as "High Priority Processing", "Dedicated Server Routing", "Data Encryption", etc. Depending on the policy selected, users need to set additional parameters. For example, if "High Priority Processing" is selected, users need to specify a specific priority value (such as a number from 1-100).
[0071] The system will immediately verify the validity of the regular expression when the user creates a model, and provide a real-time matching test function, allowing users to enter sample data to check the matching results.
[0072] S206, associating each of the custom data models with one or more of the ports, so that each port is responsible for processing service traffic matching a specific custom data model; Association refers to mapping a custom data model to a specific network port. The system provides an intuitive graphical interface that allows administrators to establish associations between models and ports by dragging and dropping. The interface displays all available custom data models and all ports in the system. Administrators can select a model and then select one or more ports to associate. The system supports many-to-many associations, that is, a model can be associated with multiple ports, and a port can also process data from multiple models.
[0073] The system uses two mapping tables internally to maintain these associations: one mapping from ports to models, and the other mapping from models to ports. This bidirectional mapping allows the system to quickly find all models associated with a specific port, or find all ports that can process specific model data.
[0074] When a packet arrives at a port, the system first looks for all models associated with the port. Then, it tries to use the regular expressions of these models to match the characteristics of the packet (such as header information or a specific part of the payload). If a matching model is found, the system applies the processing policy specified by the model. If multiple models match, the system applies the policy of the model with the highest priority.
[0075] The system implements a dynamic reconfiguration mechanism that allows administrators to add, remove, or modify the association of models to ports without stopping the system. When administrators update the association, the system immediately applies the changes to the in-memory mapping table and asynchronously persists these changes to the database. The system uses a read-write lock mechanism to ensure that ongoing packet processing operations are not affected when the association is updated.
[0076] S207, parsing the inputted business flow data and extracting data features; Business traffic data refers to various types of data packets transmitted through the network, including but not limited to HTTP requests, database queries, file transfers, etc. Data features are structured information extracted from business traffic data in the previous step. In this step, the diversion processing system first receives the original data packets transmitted in the network. The system uses deep packet inspection (DPI) technology to parse these data packets. DPI technology can analyze the content of the data packet, not just the header information. The system first identifies the protocol used by the data packet, such as TCP, UDP, HTTP, FTP, etc. Then, according to the different protocol types, the system uses the corresponding parser to extract data features. For HTTP traffic, the system extracts the request method, URL, and request header information; for database queries, the system identifies the type of SQL statement (SELECT, INSERT, UPDATE, etc.); for file transfers, the system identifies the file type and size. The system also analyzes the source IP address and destination IP address of the data packet, as well as the source port and destination port. For encrypted traffic, the system attempts to identify the encryption protocol used (such as SSL / TLS) and extracts available metadata.
[0077] In this step, the diversion processing system will compare the data features extracted in the previous step with all the custom data models stored in the system. The system first converts the data features into string form, such as concatenating the various components of the HTTP request (method, URL, header information, etc.) into a long string. Then, the system traverses all custom data models and performs the following operations on each model: reads the regular expression of the model, compiles the regular expression into an automaton using an efficient regular expression engine (such as RE2), and uses the compiled automaton to match the data feature string. When the first successfully matched model is found, the system will immediately mark it as the "first data model" and record the detailed information of the match, including the specific location of the match and the captured group.
[0078] S208, matching the data feature with the regular expression of each of the custom data models to obtain a first data model; The first data model is the custom data model that successfully matches the data features in the previous step. The processing strategy is a set of rules pre-defined for each custom data model, which guides the system on how to handle data traffic matching the model. The service priority collection is a list of different service types and their corresponding priorities. Ports here refer to the physical or logical interface on the network device for data transmission. For example, the first data model is the "financial transaction model", and its corresponding processing strategy is "high priority processing", and in the service priority collection, the priority of the financial transaction service is set to 95 (out of 100).
[0079] In this step, the traffic diversion processing system first confirms whether the match in the previous step is successful. If the match is successful, the system will immediately perform the following operations to extract the processing strategy associated with it from the first data model. This strategy contains multiple instructions, such as priority setting, bandwidth allocation, security processing, etc. The system queries the service priority collection to determine the priority of the service to which the current data traffic belongs. If the first data model has already specified a priority, the system will compare it with the value in the service priority collection and take the higher one. 3) The system selects a suitable port for data distribution based on the processing strategy and the determined priority. This selection process will take into account multiple factors: the current load of the port, the processing capacity of the port, the association with the data model, etc.
[0080] S209: When the match is successful, the successfully matched business traffic data is allocated to the corresponding port according to the processing strategy corresponding to the first data model and the business priority set.
[0081] The first data model is a custom data model that successfully matches the data features in the previous step. This model contains identification rules and processing guidelines for specific types of data traffic. The processing strategy is a set of specific operating instructions associated with the first data model, which defines how to handle data traffic that matches the model. These strategies include but are not limited to priority setting, bandwidth allocation, security processing, etc. The business priority collection is a predefined list that contains various business types and their corresponding priority values. For example, assuming that the first data model identifies a data flow as financial transaction data, its corresponding processing strategy is "high priority processing" and "encrypted transmission", and in the business priority collection, the priority of financial transaction business is set to 95 (out of 100).
[0082] In this step, the traffic diversion processing system first confirms that the data features match the first data model successfully. Then, the system immediately performs the following sequence of operations: extract the associated processing strategy from the first data model. In this example, the strategy includes "high priority processing" and "encrypted transmission". The system queries the service priority collection and obtains the priority value of 95 for the financial transaction service. According to the processing strategy and priority value, the most suitable one is selected from the available ports.
[0083] S210, monitoring the actual load data of each port in real time, and comparing it with the predicted load data; A port is an interface on a network device for data transmission, which can be a physical port or a logical port. Each port has its specific data processing capacity and current working status. Actual load data refers to the amount of data actually processed by the port at the current moment, usually measured in bytes or packets transmitted per second. Predicted load data is the load that the system predicts the port may bear in the future based on historical data and various algorithms. For example, the actual load of a port is 100Mbps per second, while the predicted load is 80Mbps per second.
[0084] In this step, the traffic diversion processing system implements a comprehensive and continuous monitoring mechanism. The system collects actual load data for each port once a second. This data includes but is not limited to: the amount of data transmitted (number of bytes), the number of packets processed, the current bandwidth usage, CPU usage, memory usage, etc. The system uses high-precision network monitoring tools (such as NetFlow or sFlow) to collect this data to ensure the accuracy and real-time nature of the data. At the same time, the system obtains the predicted load data at the corresponding time point from its prediction model.
[0085] S211. When it is detected that the deviation between the actual load data and the predicted load of any port exceeds a preset threshold, the resource allocation and the distribution ratio of the business traffic between the ports are dynamically adjusted according to the actual load data, the predicted load data and the business priority of each port, and adjusted to within the preset load balancing threshold. The preset load balancing threshold is the maximum allowable deviation percentage between the actual load data of each port and its predicted load data.
[0086] The actual load data refers to the amount of data currently actually processed by the port, usually measured in bytes or packets processed per second. The distribution ratio of business traffic refers to the process of distributing different types of business data to each port in a certain proportion. The preset load balancing threshold is a maximum allowable deviation range. The goal of system adjustment is to keep the load of all ports within this range. For example, if the preset threshold is set to 15% and the preset load balancing threshold is set to 10%, then when the actual load of a port is 20% higher than the predicted load, the system will adjust until the deviation between the actual load and the predicted load of all ports does not exceed 10%.
[0087] In this step, the offload processing system implements a complex dynamic load balancing and resource adjustment mechanism. The system first continuously monitors the actual load data of each port and compares it with the predicted load data in real time. When the system detects that the deviation between the actual load and the predicted load of any port exceeds the preset threshold (for example, 15%), the adjustment process is immediately triggered.
[0088] S212, detecting the operating status of all ports, and if a first port is in a fault state, obtaining first service flow information of the first port, where the first service flow information includes a service type, service data, and service priority of all the service data; A port is an interface on a network device used for data transmission. It can be a physical port or a logical port. Each port has its specific operating status, including normal, faulty, overloaded, etc. The first port refers to the first port found to be in a faulty state during the detection process. The faulty state means that the port cannot process data traffic normally, which may be caused by hardware failure, software error or configuration problem. The first service traffic information refers to the detailed information set of all service data transmitted through the first port. The service type indicates the specific service category to which the data traffic belongs, such as web browsing, video streaming, financial transactions, etc. Service data refers to the actual transmitted data content and its metadata. Service priority refers to the importance level assigned to each service type or each data packet, which is used to determine the processing order when resources are limited.
[0089] Specifically, the traffic diversion processing system implements a comprehensive and continuous port status monitoring mechanism. The system performs a comprehensive scan every 5 seconds to check the operating status of all ports. The inspection content includes but is not limited to: physical connection status, data transmission capacity, error packet rate, packet loss rate, delay and other indicators. For each port, the system maintains a status counter to record the number of consecutive fault detections. When a port is detected as abnormal for 3 consecutive times (15 seconds), the system marks it as a fault state. Once the system detects that the first port (for example, port 3) is in a fault state, the administrator is notified of the fault through multiple channels (such as system console, email, and SMS).
[0090] It is understandable that step S212 may be performed after step S211 or after step 204, which is not limited here.
[0091] S213: Analyze the current load status and remaining processing capacity of other target ports, where the other target ports are ports operating normally except the first port.
[0092] Other target ports refer to all normal operating ports in the system except the faulty port (the first port). Current load status refers to the working status of each target port at the current moment, including the amount of data being processed, the number of active connections, CPU usage, memory usage, etc. Remaining processing capacity refers to the amount of additional data processing that each target port can undertake without affecting the current business, expressed in the form of available bandwidth, idle CPU time or available memory.
[0093] In this step, the target port set is first determined, that is, all normal operating ports except the faulty port. Real-time data of the ports is collected once a second, including current bandwidth usage, packet processing rate, number of active connections, CPU usage, memory usage, etc. Historical data in the past hour is retrieved to analyze the load change trend. Time series analysis techniques (such as moving average and exponential smoothing) are used to predict load changes in the short term (such as the next 5 minutes). The remaining processing capacity is calculated based on the maximum processing capacity of the port (such as maximum bandwidth, peak packet processing rate) and the current load. The type of business currently processed by each target port is analyzed to evaluate whether it is suitable for receiving specific business traffic of the faulty port. For example, some ports may be specially configured to process encrypted traffic and are more suitable for receiving services that require secure transmission. The system calculates a comprehensive performance indicator for each target port, which takes into account the current load, remaining capacity, historical stability, and business compatibility.
[0094] S214. Based on a dynamic load balancing algorithm, the first service traffic of the first port is reallocated to the other target ports one by one in descending order of the service priorities.
[0095] In this step, the diversion processing system performs a complex traffic redistribution process. First, the system creates a task list sorted by business priority from high to low based on the first business traffic information collected previously, and uses a machine learning model (such as an LSTM neural network) to predict the traffic changes of this business type in the next 5 minutes. According to the predicted traffic and business characteristics (such as bandwidth requirements and processing complexity), the required amount of resources is calculated, and a multi-objective optimization algorithm is used to consider the remaining capacity, current load, business compatibility and network topology of each target port to select the most appropriate set of target ports. Using software-defined networking (SDN) technology, the flow table of the network device is dynamically updated to redirect the business traffic to the selected target port according to business priority.
[0096] S215: Calculate the new load level of each of the other target ports in real time.
[0097] This step is to monitor and calculate the new load levels of other normally operating ports in real time after reallocating the service traffic of the faulty port. The calculation of the new load level may include multiple indicators, such as CPU usage, memory usage, network bandwidth utilization, etc.
[0098] Collect real-time data of each target port, including CPU usage, memory occupancy, and network bandwidth usage, etc. At the same time, obtain the service traffic data newly assigned to the port, and then calculate the new CPU load, memory load, and network load respectively. The calculation method is to add the current usage rate to the estimated demand of the new service, and then divide it by the total capacity to get the percentage. Then, the system combines the new CPU load, memory load, and network load through the preset weight coefficient to calculate a comprehensive new load level.
[0099] S216: If the new load level of the first target port exceeds a preset load balancing threshold, the first service flow is stored in a priority queue.
[0100] The first target port refers to the first port that receives the newly allocated service traffic during the traffic redistribution process. The new load level refers to the overall workload status of the port after receiving the newly allocated service traffic, usually expressed as a percentage.
[0101] Specifically, for the marked "first target port", the system will identify the business traffic (first business traffic) originally planned to be allocated to it, suspend allocating this part of the business traffic to the port, create or access a predefined priority queue data structure, and encapsulate the relevant information of the first business traffic (such as business ID, data volume, priority, etc.) into a data object, and insert this data object into the priority queue. The insertion position is determined based on the priority of the business.
[0102] S217: Allocate the service traffic in the priority queue according to a preset time interval.
[0103] Specifically, the traffic diversion processing system implements a periodic queue processing mechanism. The system first sets a timer with an interval of 10 seconds. Whenever the timer is triggered, the system performs the following sequence of operations: First, check the current status of the priority queue, including the queue length, the waiting time of the first element in the queue, the distribution of each priority service in the queue, etc. Perform a comprehensive load scan on all target ports and collect real-time load data for each port, including CPU usage, memory usage, bandwidth utilization, etc. Based on the queue status and port load data, the system uses a multi-objective optimization algorithm to calculate the optimal allocation strategy and allocate the service traffic in the priority queue according to the allocation strategy. The following describes the flow separation processing system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of a physical device structure of a diversion processing system in an embodiment of the present application.
[0104] It should be noted that Figure 3 The structure of the diversion processing system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0105] like Figure 3 As shown, the flow processing system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0106] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0107] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.
[0108] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.
[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.
[0110] Specifically, the traffic diversion processing system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the traffic diversion processing method provided in the above embodiment is implemented.
[0111] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the flow-dividing processing system described in the above embodiment; or may exist independently without being assembled into the flow-dividing processing system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the flow-dividing processing system, the flow-dividing processing system implements the flow-dividing processing method provided in the above embodiment.
[0112] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
[0113] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.
[0114] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.
Claims
1. A diversion processing method, characterized in that: Applied to a diversion processing system, the method comprises: Obtaining historical service load data of each port, and analyzing the historical load data based on a pattern recognition algorithm to obtain common traffic patterns and peak time periods; Based on the common traffic pattern and the peak time period, the service load data within the preset time period is predicted to obtain a predicted load data collection, wherein the predicted load data collection includes the predicted load data of each of the ports; Obtaining service type information, processing scale information and urgency information of the current service in each port, and calculating service priorities of all the current services according to the service type information, the processing scale information and the urgency information to obtain a service priority set; Processing resources are allocated to each of the ports based on the predicted load data set and the service priority set, and input service traffic is allocated based on the processing resources and service priorities.
2. The method according to claim 1, characterized in that The step of predicting the service load data within a preset time period based on the common traffic pattern and the peak time period specifically includes: Classifying the common traffic patterns to obtain multiple traffic pattern types; Setting a corresponding prediction model for each type of traffic pattern, wherein different types of traffic patterns correspond to different prediction models; Dividing the preset time period into a plurality of time units, and determining a flow pattern type to which each of the time units belongs; Selecting a corresponding prediction model according to the traffic pattern type to which each of the time units belongs; Inputting historical data of the same period into the selected forecasting model to obtain forecast load data for each of the time units; The predicted load data are merged to obtain a set of predicted load data within the preset time period.
3. The method according to claim 1, characterized in that The step of calculating the service priorities of all the current services according to the service type information, the processing scale information and the urgency information specifically includes: Classifying the service type information, dividing the service type into a first service, a second service and a third service, and assigning different weight coefficients to each of them; Calculating a resource consumption index for each business according to the processing scale information, wherein the resource consumption index is proportional to the processing scale; Setting a time sensitivity coefficient based on the urgency information; Multiplying the weight coefficient, the resource consumption index and the time sensitivity coefficient to obtain a priority score; All the current services are sorted according to the priority scores to obtain a service priority set.
4. The method according to claim 1, characterized in that: After the step of allocating processing resources to each of the ports based on the set of predicted load data and the set of service priorities, the method further includes: Receiving a plurality of user-defined custom data models, each of the custom data models comprising a regular expression and a corresponding processing strategy; Associating each of the custom data models with one or more of the ports, so that each port is responsible for processing business traffic matching a specific custom data model; Analyze the input business traffic data and extract data features; Matching the data feature with the regular expression of each of the custom data models to obtain a first data model; When the match is successful, the successfully matched business traffic data is allocated to the corresponding port according to the processing strategy corresponding to the first data model and the business priority set.
5. The method according to claim 4, characterized in that After the step of allocating the successfully matched service flow data to the corresponding port according to the processing strategy corresponding to the first data model and the service priority set, the method further includes: Monitor the actual load data of each port in real time and compare it with the predicted load data; When it is detected that the deviation between the actual load data and the predicted load of any port exceeds a preset threshold, the resource allocation and the distribution ratio of business traffic between ports are dynamically adjusted according to the actual load data, the predicted load data and the business priority of each port to within the preset load balancing threshold. The preset load balancing threshold is the maximum allowable deviation percentage between the actual load data of each port and its predicted load data.
6. The method according to claim 1, characterized in that After the step of allocating processing resources to each of the ports based on the set of predicted load data and the set of service priorities, the method further includes: Detecting the running status of all ports, and if a first port is in a fault state, obtaining first service flow information of the first port, where the first service flow information includes a service type, service data, and service priority of all the service data; Analyzing current load conditions and remaining processing capacity of other target ports, where the other target ports are ports operating normally except the first port; Based on a dynamic load balancing algorithm, the first service traffic of the first port is redistributed to the other target ports one by one in the order of the service priorities from high to low.
7. The method according to claim 6, characterized in that After the step of reallocating the service traffic of the first port to the other normal operating ports one by one in the order of the service priorities from high to low based on the dynamic load balancing algorithm, the method further includes: calculating in real time a new load level for each of the other target ports; If the new load level of the first target port exceeds a preset load balancing threshold, storing the first service flow in a priority queue; The service traffic in the priority queue is distributed according to a preset time interval.
8. A flow separation processing system, characterized in that: The diversion processing system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the diversion processing system to execute the method described in any one of claims 1-7.
9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the offload processing system, the offload processing system is caused to execute the method according to any one of claims 1 to 7.
10. A computer program product, characterized in that When the computer program product is executed on a flow-bypass processing system, the flow-bypass processing system is caused to execute the method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Green intelligent computing center energy efficiency optimization method and system
CN117539726A
Multivariate computing power comprehensive management scheduling method and system for intelligent computing center
CN117950868A
TSN network medium system for realizing precise flow control
CN118474039A
Flow scheduling method and system for multi-core SDN (Software Defined Network) switch
CN118509373A
Dynamic queue management of network traffic
US20230155964A1
Cited By
Task scheduling optimization analysis method and system based on big data
CN119883580A
Hospital multi-activity data center network management system based on software defined network
CN120075258A
Information docking method based on mall applet
CN120378368A
Information docking method based on mall applet
CN120378368B
Network congestion prediction method based on DPI data and related products
CN120416168A
