CN116192857A - Encryption traffic load balancing method based on multilayer perceptron - Google Patents
Encryption traffic load balancing method based on multilayer perceptron Download PDFInfo
- Publication number
- CN116192857A CN116192857A CN202211567966.4A CN202211567966A CN116192857A CN 116192857 A CN116192857 A CN 116192857A CN 202211567966 A CN202211567966 A CN 202211567966A CN 116192857 A CN116192857 A CN 116192857A
- Authority
- CN
- China
- Prior art keywords
- load balancing
- service
- server
- layer perceptron
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1014—Server selection for load balancing based on the content of a request
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an encryption traffic load balancing method based on a multi-layer perceptron, which comprises the following steps: the load balancing server is connected in series in the network, and receives the data packet sent by the client; the load balancing module is configured with input service resources and static priority; calculating the dynamic priority of each service server by using the multi-layer perceptron encryption flow classification server, and transmitting the calculated dynamic priority back; the load balancing server classifies the received data packets by using a multi-layer perceptron encryption traffic classification method so as to determine encryption application types and select a load balancing module; selecting an optimal business server by combining the static priority and the dynamic priority; and the load balancing server forwards the data packet sent by the client to the selected optimal service server, obtains a service processing result and forwards the service processing result to the client. The method of the invention improves the performance and the reliability of the service system on the premise of not expanding the capacity of the service system and not increasing the investment of the service equipment.
Description
Technical Field
The invention relates to an encryption traffic load balancing method based on a multi-layer perceptron, and belongs to the technical field of network transmission.
Background
A Multi-layer Perceptron (MLP) performs encrypted traffic identification based on a Multi-layer neural network. Except for detecting and analyzing only five-tuple information of the IP packet with a common message, including a source address, a destination address, a source port, a destination port and a protocol type, the multi-layer perceptron obtains a classifier through learning and training a large number of encrypted traffic samples, thereby identifying various applications and contents thereof. With the rapid development of Internet networks, various traffic and application types are increasing, especially for access to data centers, large enterprises, e-commerce websites, and the like. Most websites require uninterrupted 24-hour service, and any loss of critical data in the service terminals or communications can cause direct business loss. The traditional load balancing system controls based on the source and destination IP addresses, ports and protocol types of the network layer data packets, cannot distribute traffic to each server based on the content and behavior of application data, and cannot meet the requirement of network development more and more, analyzes the data packets from the application layer and performs load balancing, so that the stability and smoothness of the network can be ensured.
The current small and medium-sized local area networks account for 80% of the total number of global local area networks, and how to perform effective load balancing on the small and medium-sized local area networks becomes a problem to be solved urgently.
Disclosure of Invention
The invention aims to solve the technical problems of overcoming the defects of the prior art, providing an encryption traffic load balancing method based on a multi-layer perceptron, and solving the problems that the existing method cannot distribute traffic to each server based on the content and the behavior of application data, cannot analyze data packets from an application layer and perform load balancing, so that a network is unstable and transmission congestion is easy to exist.
The technical scheme adopted by the invention specifically solves the technical problems as follows:
an encryption traffic load balancing method based on a multi-layer perceptron comprises the following steps:
step 1, connecting a load balancing server in a network in series, and receiving a data packet containing a service request sent by a client;
step 2, the load balancing server configures input service resources and static priorities for the load balancing module of each type of protocol in the load balancing server;
step 3, connecting the load balancing server by using the multi-layer perceptron encryption flow classifying server to obtain service processing time delay and service processing results of service servers in the network, calculating dynamic priorities of the service servers, and transmitting the calculated dynamic priorities back to the load balancing server as a basis for selecting the optimal service servers;
step 4, the load balancing server analyzes the service request in the received data packet by utilizing a multi-layer perceptron deep message detection method to analyze the application message and match the characteristic character string so as to determine the application type and select a load balancing module; the selected load balancing module combines the static priority and the dynamic priority to select the optimal service end;
and 5, forwarding the data packet sent by the client to the selected optimal service server by the load balancing server, obtaining a service processing result by the optimal service server and returning the service processing result, and forwarding the service processing result to the client for sending the data packet by the load balancing server.
Further, as a preferable technical scheme of the invention: and in the step 2, the load balancing module configures and inputs a plurality of service resources to form a service resource pool.
Further, as a preferable technical scheme of the invention: and selecting the optimal business service end in the step 4 comprises sorting from low to high according to the dynamic priority, and selecting the business service end with the smallest numerical value as the optimal business service end.
Further, as a preferable technical scheme of the invention: and step 4, selecting the service end with the largest static priority value as the optimal service end when the same service end with the smallest dynamic priority value exists.
By adopting the technical scheme, the invention can produce the following technical effects:
the invention provides an encryption traffic load balancing method based on a multi-layer perceptron, which improves the response performance and reliability of a service system by identifying and analyzing application messages by the multi-layer perceptron.
The method of the invention has the following advantages:
(1) The method processes the service application message by using a multi-layer perceptron mode, and is suitable for customizing specific services in an enterprise environment. The method has the advantages of being high in server resource utilization rate, quick in response time and the like, and the special user can obtain the response of the service preferentially, the special application request can be processed preferentially, and the like. The method fills the blank that the general load balancing system can only load balance according to methods such as IP+ports and the like, but cannot implement load balancing according to the application type of the request message.
(2) The method of the invention ensures that the service system has better high concurrency capability, and the service throughput and the waiting time are improved.
(3) The method of the invention improves the corresponding performance and reliability of the service system on the premise of not expanding the capacity of the service system and not increasing the investment of the service equipment.
Drawings
Fig. 1 is a schematic diagram of an encryption traffic load balancing method based on a multi-layer perceptron.
FIG. 2 is a schematic diagram of application type logic of the present invention.
Fig. 3 is a schematic diagram of a preferred service end of the present invention.
Detailed Description
Embodiments of the present invention will be described below with reference to the drawings.
As shown in fig. 1 and 2, the invention designs an encryption traffic load balancing method based on a multi-layer perceptron, wherein in the method, a transmission network comprises a plurality of clients and business servers, and on the basis, a load balancing server and a multi-layer perceptron encryption traffic classification server are additionally arranged to finish encryption traffic load balancing in a system. Specifically, the method of the invention comprises the following steps:
and step 1, connecting the load balancing server in a network in series, and receiving a data packet containing a service request sent by a client.
The load balancing server is connected in series in the original network and is mainly responsible for distributing service request data packets and returning service response data, providing uniform service IP (Internet protocol) and receiving preset various message data.
And step 2, the load balancing server configures input service resources and static priorities for the load balancing module of each type of protocol in the server.
The load balancing server is internally provided with a specific load balancing module aiming at each type of protocol, each type of module comprises service resources and static priorities of the service resources, and the service resources and the static priorities are input through configuration; the configuration input of a number of service resources may form a service resource pool.
Step 3, the multi-layer perceptron encryption flow classification server is used for connecting with a load balancing server, and the load balancing server transmits the flow of the business service end in the network to the multi-layer perceptron encryption flow classification server through light splitting or mirroring; the multi-layer perceptron encryption flow classification server is used as an index auxiliary system and is used for acquiring service processing time delay and service processing results of service servers in a network, calculating dynamic priorities of the service servers, and transmitting the calculated dynamic priorities back to the load balancing server to be used as a basis for selecting an optimal service server.
The multi-layer perceptron encryption flow classification server sets dynamic priority for each service resource in the packet according to the network condition of each resource in the service resource pool, the number of active services, the response codes of service processing and the like. Specifically, according to the service processing time delay and the service processing result of the service server of the acquired network, the dynamic priority of each service server is calculated by multiplying the failure service times by (average service processing time delay +2 times variance), and finally the dynamic priority is transmitted back to the load balancing system as the basis for selecting the optimal service server; the calculation formula is as follows:
wherein μ represents the average delay, x represents the response delay, σ 2 Representing variance and N representing failure times.
Step 4, the load balancing server analyzes the service request in the received data packet by utilizing a multi-layer perceptron deep message detection method to analyze the application message and match the characteristic character string so as to determine the application type and select a load balancing module; the selected load balancing module combines the static priority and the dynamic priority to select the optimal service end, and selects the most appropriate service end in the resource pool, thereby improving the performance and reliability of the loaded service.
The method for selecting the optimal business service end comprises the following steps:
and selecting the service end with the smallest value as the optimal service end according to the sequence from low to high of the dynamic priority.
And when the same several service servers with the minimum dynamic priority values exist, the service server with the maximum static priority value is preferably selected as the optimal service server.
And 5, forwarding the data packet sent by the client to the selected optimal service server by the load balancing server, obtaining a service processing result by the optimal service server and returning the service processing result, and forwarding the service processing result to the client for sending the data packet by the load balancing server, wherein the principle is as shown in fig. 3, respectively determining the optimal service server from the server cluster 1 and the server cluster 2, forwarding the data packet sent by the client to the optimal service server, and receiving the service processing result from the optimal service server.
In conclusion, the method of the invention processes the service application message by using a multi-layer perceptron mode, and is suitable for customizing specific services in an enterprise environment. The method has the advantages of being high in server resource utilization rate, quick in response time and the like, and the special user can obtain the response of the service preferentially, the special application request can be processed preferentially, and the like. The method fills the blank that the general load balancing system can only load balance according to methods such as IP+ports and the like, but cannot implement load balancing according to the application type of the request message. The method of the invention improves the corresponding performance and reliability of the service system on the premise of not expanding the capacity of the service system and not increasing the investment of the service equipment.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the spirit of the present invention.
Claims (4)
1. The encryption traffic load balancing method based on the multi-layer perceptron is characterized by comprising the following steps of:
step 1, connecting a load balancing server in a network in series, and receiving a data packet containing a service request sent by a client;
step 2, the load balancing server configures input service resources and static priorities for the load balancing module of each type of encryption protocol in the load balancing server;
step 3, connecting the load balancing server by using the multi-layer perceptron encryption flow classifying server to obtain service processing time delay and service processing results of service servers in the network, calculating dynamic priorities of the service servers, and transmitting the calculated dynamic priorities back to the load balancing server as a basis for selecting the optimal service servers;
step 4, the load balancing server analyzes the service request in the received data packet by utilizing a multi-layer perceptron deep message detection method to analyze the application message and match the characteristic character string so as to determine the application type and select a load balancing module; the selected load balancing module combines the static priority and the dynamic priority to select the optimal service end;
and 5, forwarding the data packet sent by the client to the selected optimal service server by the load balancing server, obtaining a service processing result by the optimal service server and returning the service processing result, and forwarding the service processing result to the client for sending the data packet by the load balancing server.
2. The encrypted traffic load balancing method based on the multi-layer perceptron as claimed in claim 1, wherein: and in the step 2, the load balancing module configures and inputs a plurality of service resources to form a service resource pool.
3. The encrypted traffic load balancing method based on the multi-layer perceptron as claimed in claim 1, wherein: and selecting the optimal business service end in the step 4 comprises sorting from low to high according to the dynamic priority, and selecting the business service end with the smallest numerical value as the optimal business service end.
4. The encrypted traffic load balancing method based on the multi-layer perceptron as claimed in claim 3, wherein: and step 4, selecting the service end with the largest static priority value as the optimal service end when the same service end with the smallest dynamic priority value exists.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211567966.4A CN116192857A (en) | 2022-12-07 | 2022-12-07 | Encryption traffic load balancing method based on multilayer perceptron |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211567966.4A CN116192857A (en) | 2022-12-07 | 2022-12-07 | Encryption traffic load balancing method based on multilayer perceptron |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116192857A true CN116192857A (en) | 2023-05-30 |
Family
ID=86431529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211567966.4A Pending CN116192857A (en) | 2022-12-07 | 2022-12-07 | Encryption traffic load balancing method based on multilayer perceptron |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116192857A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116723154A (en) * | 2023-07-03 | 2023-09-08 | 乘乘智数科技(深圳)有限公司 | Route distribution method and system based on load balancing |
-
2022
- 2022-12-07 CN CN202211567966.4A patent/CN116192857A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116723154A (en) * | 2023-07-03 | 2023-09-08 | 乘乘智数科技(深圳)有限公司 | Route distribution method and system based on load balancing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10680951B2 (en) | System and method for processing and forwarding transmitted information | |
US7647393B2 (en) | Server load balancing apparatus and method using MPLS session | |
US7089294B1 (en) | Methods, systems and computer program products for server based type of service classification of a communication request | |
CN103444137B (en) | Priority network business | |
US6178453B1 (en) | Virtual circuit switching architecture | |
US7290028B2 (en) | Methods, systems and computer program products for providing transactional quality of service | |
US10257290B2 (en) | Systems and methods for data routing management | |
JP6162337B2 (en) | Application-aware network management | |
US20220029924A1 (en) | Determining traceability of network traffic over a communications network | |
CN102377640B (en) | Message processing apparatus, message processing method and preprocessor | |
US20070130367A1 (en) | Inbound connection prioritization | |
US20040098499A1 (en) | Load balancing system | |
US10715449B2 (en) | Layer 2 load balancing system | |
US8577984B2 (en) | State management in a distributed computing system | |
US20020136204A1 (en) | Method and system for routing network traffic based upon application information | |
CN116192857A (en) | Encryption traffic load balancing method based on multilayer perceptron | |
CN107864189A (en) | A kind of application layer traffic load-balancing method based on DPI | |
CN116723154A (en) | Route distribution method and system based on load balancing | |
CN113422699B (en) | Data stream processing method and device, computer readable storage medium and electronic equipment | |
US8307112B2 (en) | Mediated information flow | |
CN112637090A (en) | Dynamic multilevel flow control method based on programmable switching chip | |
CN110430172B (en) | Internet protocol content restoration system and method based on dynamic session association technology | |
US20230239247A1 (en) | Method and system for dynamic load balancing | |
CN116260855B (en) | Communication method, communication device, electronic equipment and storage medium | |
US20230171286A1 (en) | Bridging between client and server devices using proxied network metrics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |