Load balancing control method based on data traffic

Abstract

The invention discloses a load balancing control method based on data traffic, and relates to the technical field of data transmission. Comprising the following steps: constructing a flow monitoring module based on data flow, constructing a self-adaptive flow classification model, dynamically allocating weights to load nodes with balanced loads, dynamically adjusting a transmission path of the flow, carrying out real-time load balancing scheduling, and processing abnormal flow. According to the load balancing control method based on the data traffic, the self-adaptive traffic classification model and the multi-path traffic reconstruction algorithm are introduced, so that the defects in the prior art are fundamentally overcome. The real-time performance, the stability and the resource utilization rate of the system are remarkably improved through deep classification of the traffic characteristics and a multi-path dynamic segmentation strategy. According to the method, resource allocation can be optimized in a complex traffic scene, the load balancing efficiency is improved, meanwhile, the service quality of delay-sensitive and bandwidth-intensive services is guaranteed, and the availability and reliability of the whole system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and in particular to a load balancing control method based on data flow. Background Art

[0002] With the continuous growth of Internet traffic and the diversification of business needs, load balancing technology plays a vital role in modern distributed systems. Traditional load balancing methods mainly rely on fixed traffic distribution rules or simple load detection mechanisms, which cannot fully cope with the complex changes and sudden growth of real-time traffic. In existing technologies, the following deficiencies are particularly obvious: Classification is not sophisticated enough: Existing traffic classification models are often based on static rules or simple classification algorithms, which make it difficult to dynamically adapt to diverse business scenarios, such as the mixed processing of delay-sensitive and bandwidth-intensive traffic.

[0003] Single path scheduling: Existing load balancing technologies often use single path scheduling, ignoring the potential of multi-path transmission and failing to fully utilize network resources to improve system throughput and stability. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a load balancing control method based on data traffic to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a load balancing control method based on data traffic, comprising the following steps: S1. Build a traffic monitoring module based on data traffic; S2, classify the traffic collected by the traffic monitoring module and build an adaptive traffic classification model; S3. Dynamically assign weights to each load node of load balancing according to the traffic classification results; S4, dynamically adjust the traffic transmission path according to the real-time status of the load node; S5: Based on the results of traffic classification, weight adjustment and path planning, real-time load balancing scheduling is performed; S6. In load balancing, handle abnormal traffic.

[0006] To further optimize the technical solution, in step S1, the flow monitoring module is configured with multiple probe nodes, covering all paths of the network, to ensure that comprehensive and accurate flow information is collected; The traffic monitoring module dynamically monitors the traffic of all paths in the network based on probe nodes.

[0007] To further optimize the technical solution, in step S2, the adaptive traffic classification model includes: Multimodal representation of traffic characteristics; Fuzzy attribution calculation; Dynamic weight adjustment; Final classification decision.

[0008] To further optimize the technical solution, the multimodal representation of the traffic characteristics includes: Set the feature set of the traffic collected by the traffic monitoring module to , where each Indicates a feature; The features are normalized and encoded and mapped into a high-dimensional modal space. The mapping process is as follows: ; in, It is The feature vector of a traffic sample; It is a sample In Features The value on is given by the mapping function Processed; The fuzzy attribution degree calculation includes: The obtained traffic sample feature vector and classification category center point Compare and calculate samples Belongs to category The fuzzy belonging degree of The dynamic weight adjustment includes: Dynamically adjust the weight of each category , the weight adjustment is based on the real-time traffic load, and the calculation formula is as follows: ; in, :category Dynamic weight of :category The current traffic share of : Global average traffic share; : Sensitivity parameter, used to adjust the sensitivity of weight changes; The final classification decision includes: Combining fuzzy attribution and dynamic weight , calculate the comprehensive score of each category, assign the sample to the category with the highest score, and output the final classification result.

[0009] Further optimize this technical solution, the calculation sample Belongs to category When the fuzzy attribution degree is , the calculation formula is as follows: ; in, :sample For Category The fuzzy belonging degree of is in the range of [0,1]; : Euclidean distance between sample features and category center; :category The fuzzy parameters control the scope and accuracy of fuzzy classification; Combined with fuzzy attribution and dynamic weights , calculate the comprehensive score of each category, the calculation formula is as follows: ; in, :sample The final classification result; : Fuzzy attribution, reflecting the similarity between the characteristics of the sample and the category; : Dynamic weight, reflecting the current load status of the category.

[0010] To further optimize the technical solution, in step S3, the load carrying capacity of each load node is calculated by analyzing the characteristics of different types of traffic, including stability, burstiness and sensitivity; Based on real-time traffic monitoring data and historical trend forecasts, when a sudden increase in traffic is detected in a short period of time, the weight of the backup load node is increased in advance to relieve the pressure on the main load node.

[0011] To further optimize the technical solution, in step S4, a multi-path traffic reconstruction algorithm is used to allow part of the traffic to be transmitted using multiple paths at the same time, so as to increase the stability and throughput of the transmission; In the multipath traffic reconstruction algorithm, the following parameters are defined: : Total traffic feature vector, including multi-dimensional attributes, including delay sensitivity and bandwidth requirements; : A set of available paths, where Indicates Paths; :path The quality index is defined as: ; in: :path Delays; :path jitter; :path Packet loss rate; : Weight parameter, satisfying ; : Traffic split ratio, satisfying: ; : Assigned to the path traffic subset.

[0012] To further optimize the technical solution, the multi-path traffic reconstruction algorithm includes: Path priority calculation; Initial traffic split ratio; Adjustment of business characteristics; Dynamic balance correction.

[0013] To further optimize the technical solution, in step S5, the central control node is used to collect the status information of each load node in real time and dynamically allocate data traffic; To cope with sudden traffic, based on the fast fallback mechanism, when a load node is overloaded, the traffic is immediately transferred to the backup load node or the idle resource pool.

[0014] To further optimize the technical solution, in step S6, a traffic analysis model based on deep learning is used to accurately identify abnormal traffic and determine the source and threat type of abnormal traffic; Once abnormal traffic is confirmed, the relevant load nodes are immediately isolated and the routing of legitimate traffic is reassigned.

[0015] In a second aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a load balancing control method based on data traffic as described in the first aspect of the present invention are implemented.

[0016] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of a load balancing control method based on data traffic as described in the first aspect of the present invention are implemented.

[0017] Compared with the prior art, the present invention provides a load balancing control method based on data flow, which has the following beneficial effects: This data traffic-based load balancing control method fundamentally solves the shortcomings of existing technologies by introducing an adaptive traffic classification model and a multi-path traffic reconstruction algorithm. The deep classification of traffic characteristics and the multi-path dynamic segmentation strategy significantly improve the real-time performance, stability, and resource utilization of the system. This method can optimize resource allocation and improve load balancing efficiency in complex traffic scenarios, while ensuring the service quality of delay-sensitive and bandwidth-intensive services, and enhancing the availability and reliability of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A flow chart of a load balancing control method based on data flow proposed by the present invention; Figure 2 A schematic diagram of a flow chart of an adaptive traffic classification model in a load balancing control method based on data traffic proposed by the present invention; Figure 3 A schematic flow chart of a multi-path traffic reconstruction algorithm in a data traffic-based load balancing control method proposed in the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments. Embodiment 1

[0023] Reference Figure 1 to Figure 3 , which is the first embodiment of the present invention, and provides a load balancing control method based on data traffic, comprising the following steps: S1. Build a traffic monitoring module based on data traffic In this embodiment, the traffic monitoring module is configured with multiple probe nodes, covering all paths of the network, to ensure that comprehensive and accurate traffic information is collected. An adaptive sampling frequency is set to avoid excessive overhead introduced by the traffic monitoring module and to ensure data accuracy.

[0024] The traffic monitoring module dynamically monitors the traffic of all paths in the network based on probe nodes.

[0025] S2. Classify the traffic collected by the traffic monitoring module and build an adaptive traffic classification model In this embodiment, the adaptive traffic classification model includes: Multimodal representation of traffic characteristics The multimodal representation of the traffic characteristics includes: Set the feature set of the traffic collected by the traffic monitoring module to , where each Indicates a feature; The features are normalized and encoded, mapped to a high-dimensional modal space, and feature vectors that can be processed by the classification model are generated. The mapping process is as follows: ; in, It is The feature vector of a traffic sample; It is a sample In Features The value on is given by the mapping function Processed.

[0026] Fuzzy attribution calculation The fuzzy attribution degree calculation includes: The obtained traffic sample feature vector and classification category center point Compare and calculate samples Belongs to category The fuzzy belonging degree of . The calculation formula is as follows: ; in, :sample For Category The fuzzy belonging degree of is in the range of [0,1]; : Euclidean distance between sample features and category center; :category The fuzzy parameters control the scope and accuracy of fuzzy classification.

[0027] Due to the introduction of the fuzzy attribution mechanism, samples can be classified into multiple categories at the same time (for example, some traffic may be both delay-sensitive and bandwidth-intensive), which improves the flexibility and accuracy of classification.

[0028] By fuzzy attribution, a traffic sample is allowed to partially belong to multiple categories at the same time, thereby improving the adaptability of the classification model to complex traffic.

[0029] Dynamic weight adjustment The dynamic weight adjustment includes: Dynamically adjust the weight of each category , the weight adjustment is based on the real-time traffic load, and the calculation formula is as follows: ; in, :category Dynamic weight of :category The current traffic share of : Global average traffic share; : Sensitivity parameter, used to adjust the sensitivity of weight changes.

[0030] During operation, the model monitors the traffic proportion of each category in real time and dynamically adjusts the weight through a formula. For example, when the traffic of a certain category surges, its weight will be reduced to reduce the load pressure of the category.

[0031] Ensure that the classification model is adaptable to real-time traffic changes so that it can dynamically optimize resource allocation in the load balancing strategy.

[0032] Final classification decision Combining fuzzy attribution and dynamic weight , calculate the comprehensive score of each category, assign the sample to the category with the highest score, and output the final classification result. The calculation formula is as follows: ; in, :sample The final classification result; : Fuzzy attribution, reflecting the similarity between the characteristics of the sample and the category; : Dynamic weight, reflecting the current load status of the category.

[0033] Output the final classification results to provide input for subsequent traffic scheduling and load balancing strategies.

[0034] S3. Dynamically assign weights to each load balancing node based on traffic classification results. In this embodiment, the load carrying capacity of each load node is calculated by analyzing the characteristics of different types of traffic, including stability, burstiness, and sensitivity; According to real-time traffic monitoring data and historical trend forecasts, when a sudden increase in traffic is detected in a short period of time, the weight of the backup load node is increased in advance to relieve the pressure on the main load node. The weight allocation strategy is iteratively optimized through real-time feedback.

[0035] S4. Dynamically adjust the traffic transmission path according to the real-time status of the load node In this embodiment, a multi-path traffic reconstruction algorithm is used to allow part of the traffic to be transmitted using multiple paths at the same time, so as to increase the stability and throughput of the transmission; In the multipath traffic reconstruction algorithm, the following parameters are defined: : Total traffic feature vector, including multi-dimensional attributes, including delay sensitivity and bandwidth requirements.

[0036] , each dimension Indicates an attribute of traffic.

[0037] : A set of available paths, where Indicates Paths; :path The quality index is defined as: ; in: :path Delays; :path jitter; :path Packet loss rate; : Weight parameter, satisfying ; : Traffic split ratio, satisfying: ; : Assigned to the path traffic subset.

[0038] The multipath traffic reconstruction algorithm comprises: Path priority calculation For each path Calculating priority weights , the formula is as follows: ; The better the path quality (i.e., lower latency, lower jitter, and lower packet loss), the higher its priority. The higher.

[0039] Initial traffic split ratio Based on the path priority, the traffic is initially divided:

[0040] The higher the path priority, the larger the traffic proportion initially allocated to it.

[0041] Service feature adjustment We optimize the weights of delay-sensitive traffic, bandwidth-intensive traffic and other service characteristics and adjust the split ratio. The adjusted ratio is:

[0042] in, : Business characteristic weight adjustment factor, :path Adaptability to flow characteristics.

[0043] Dynamic balance correction If some paths are congested or abnormal (such as Temporary increase), dynamic adjustment ratio:

[0044] in, : Sensitivity parameter, which determines the impact of mass change on flow splitting.

[0045] Then, the traffic is distributed to different paths in proportion, and the transmission subset is .

[0046] S5: Perform real-time load balancing scheduling based on traffic classification, weight adjustment and path planning results In this embodiment, a central control node is used to collect status information of each load node in real time and dynamically allocate data traffic; To cope with sudden traffic, based on the fast fallback mechanism, when a load node is overloaded, the traffic is immediately transferred to the backup load node or the idle resource pool.

[0047] Potential loop problems also need to be handled during the scheduling process to ensure that data flows can reach the target efficiently.

[0048] S6. In load balancing, handle abnormal traffic In this embodiment, a deep learning-based traffic analysis model (such as Transformer) is used to accurately identify abnormal traffic and determine the source and threat type (such as DDoS attack) of the abnormal traffic. Once abnormal traffic is confirmed, the relevant load nodes are immediately isolated and the routes of legitimate traffic are reallocated to ensure service continuity.

[0049] Abnormal traffic is forwarded to an isolated environment for further analysis to improve the system's security and anti-attack capabilities. Embodiment 2

[0050] This embodiment also provides a computer device, which is suitable for a load balancing control method based on data traffic, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a load balancing control method based on data traffic as proposed in the above embodiment.

[0051] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, a load balancing control method based on data flow as proposed in the above embodiment is implemented.

[0052] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0053] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0054] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0055] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0056] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0057] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A load balancing control method based on data flow, characterized in that: The following steps are involved: S1. Build a traffic monitoring module based on data traffic; S2, classify the traffic collected by the traffic monitoring module and build an adaptive traffic classification model; S3. Dynamically assign weights to each load node of load balancing according to the traffic classification results; S4, dynamically adjust the traffic transmission path according to the real-time status of the load node; S5: Based on the results of traffic classification, weight adjustment and path planning, real-time load balancing scheduling is performed; S6. In load balancing, handle abnormal traffic.

2. A load balancing control method based on data flow according to claim 1, characterized in that: In step S1, a plurality of probe nodes are configured in the flow monitoring module, covering all paths of the network, to ensure that comprehensive and accurate flow information is collected; The traffic monitoring module dynamically monitors the traffic of all paths in the network based on probe nodes.

3. The load balancing control method based on data flow according to claim 1, characterized in that: In step S2, the adaptive traffic classification model includes: Multimodal representation of traffic characteristics; Fuzzy attribution calculation; Dynamic weight adjustment; Final classification decision.

4. A load balancing control method based on data flow according to claim 3, characterized in that: The multimodal representation of the traffic characteristics includes: Set the feature set of the traffic collected by the traffic monitoring module to , where each Indicates a feature; The features are normalized and encoded and mapped into a high-dimensional modal space. The mapping process is as follows: ； in, It is The feature vector of a traffic sample; It is a sample In Features The value on is given by the mapping function Processed; The fuzzy attribution degree calculation includes: The obtained traffic sample feature vector and classification category center point Compare and calculate samples Belongs to category The fuzzy belonging degree of The dynamic weight adjustment includes: Dynamically adjust the weight of each category , the weight adjustment is based on the real-time traffic load, and the calculation formula is as follows: ； in, :category Dynamic weight of :category The current traffic share of : Global average traffic share; : Sensitivity parameter, used to adjust the sensitivity of weight changes; The final classification decision includes: Combining fuzzy attribution and dynamic weight , calculate the comprehensive score of each category, assign the sample to the category with the highest score, and output the final classification result.

5. A load balancing control method based on data flow according to claim 4, characterized in that: The calculation sample Belongs to category When the fuzzy attribution degree is , the calculation formula is as follows: ； in, :sample For Category The fuzzy belonging degree of is in the range of [0,1]; : Euclidean distance between sample features and category center; :category The fuzzy parameters control the scope and accuracy of fuzzy classification; Combined with fuzzy attribution and dynamic weights , calculate the comprehensive score of each category, the calculation formula is as follows: ； in, :sample The final classification result; : Fuzzy attribution, reflecting the similarity between the characteristics of the sample and the category; : Dynamic weight, reflecting the current load status of the category.

6. The load balancing control method based on data flow according to claim 1, characterized in that: In step S3, the load carrying capacity of each load node is calculated by analyzing the characteristics of different types of traffic, including stability, burstiness and sensitivity; Based on real-time traffic monitoring data and historical trend forecasts, when a sudden increase in traffic is detected in a short period of time, the weight of the backup load node is increased in advance to relieve the pressure on the main load node.

7. The load balancing control method based on data flow according to claim 1, characterized in that: In step S4, a multi-path traffic reconstruction algorithm is used to allow part of the traffic to be transmitted using multiple paths at the same time, so as to increase the stability and throughput of the transmission; In the multipath traffic reconstruction algorithm, the following parameters are defined: : Total traffic feature vector, including multi-dimensional attributes, including delay sensitivity and bandwidth requirements; : A set of available paths, where Indicates Paths; :path The quality index is defined as: ； in: :path Delays; :path jitter; :path Packet loss rate; : Weight parameter, satisfying ; : Traffic split ratio, satisfying: ； : Assigned to the path traffic subset.

8. A load balancing control method based on data flow according to claim 7, characterized in that: The multipath traffic reconstruction algorithm comprises: Path priority calculation; Initial traffic split ratio; Adjustment of business characteristics; Dynamic balance correction.

9. The method for load balancing control based on data flow according to claim 1, characterized in that: In step S5, the central control node is used to collect status information of each load node in real time and dynamically allocate data traffic; To cope with sudden traffic, based on the fast fallback mechanism, when a load node is overloaded, the traffic is immediately transferred to the backup load node or the idle resource pool.

10. The method for load balancing control based on data flow according to claim 1, characterized in that: In step S6, a traffic analysis model based on deep learning is used to accurately identify abnormal traffic and determine the source and threat type of the abnormal traffic; Once abnormal traffic is confirmed, the relevant load nodes are immediately isolated and the routing of legitimate traffic is reassigned.

Images