Power network flow classification device based on STM32 microcontroller

Abstract

The utility model discloses a power network flow classification device based on an STM32 microcontroller, which comprises a data processing device and a controller, the controller is respectively connected with an Ethernet port, a first serial peripheral interface and a second serial peripheral interface through a bus, and the controller adopts the STM32 microcontroller and is used for operating a classifier model. Analyzing the network data of the power system by adopting a classifier model; the flow data storage device adopts a static random access memory and is used for storing network data of the power system; and the communication control device, the radio frequency antenna and the upper computer are in wireless communication, and the communication control device is used for transmitting the analysis result of the network data of the power system. The device is simple to operate, is suitable for edge calculation of the classifier, and has universality and applicability.

Description

TECHNICAL FIELD

[0001] The utility model relates to a kind of electric power network flow classification device based on STM32 microcontroller, belong to electric power system computer technical field. BACKGROUND

[0002] With the improvement of the digitization and intelligentization of electric power system, smart grid emerges as the times require. Smart grid is based on communication and information technology, and controls each stage of power generation, transmission and consumption comprehensively. However, since smart grid relies on communication infrastructure to provide wide-area monitoring and is connected to the Internet, its vulnerability has significantly increased, so the monitoring of the safety of electric power system is increasingly important. And with the continuous expansion of China's electric power communication network, the services and applications carried by the network are increasing. By accurately identifying and analyzing network traffic, not only can the perspective ability of the carried services be enhanced, the network resource utilization rate be improved, load balancing be achieved, but also network abnormal traffic can be identified in time, and the network security control capability can be improved.

[0003] At present, with the continuous development of artificial intelligence and machine learning technology, the traffic classification method based on machine learning is more and more widely applied. The principle is to construct a classifier by statistical analysis and training of service data stream, and to extract features from input data by using it to achieve the purpose of classifying different data streams. However, the existing electric power network flow classification device cannot make the classifier work better, so the technical personnel in the field urgently need to improve the classification device applied to electric power network flow classification. UTILITY MODEL CONTENT

[0004] Purpose: In order to overcome the deficiencies in the prior art, the utility model provides an electric power network flow classification device based on STM32 microcontroller, which can provide a more efficient, low-power and easy-to-use device for the use of the classifier.

[0005] Technical solution: In order to solve the above technical problems, the utility model adopts the technical scheme that:

[0006] An electric power network flow classification device based on STM32 microcontroller, comprising: a flow data storage device, a data processing device and a communication control device.

[0007] The data processing device comprises a mainboard, a controller, an Ethernet port, a first serial peripheral interface and a second serial peripheral interface, the controller is connected to the Ethernet port, the first serial peripheral interface and the second serial peripheral interface through a bus, the controller adopts an STM32 microcontroller, is used for running a classifier model, and is used for analyzing electric power system network data by using the classifier model.

[0008] The flow data storage device comprises a first serial interface connected with a first serial peripheral interface, and the flow data storage device adopts a static random access memory for storing network data of the power system.

[0009] The communication control device comprises a second serial interface connected with a second serial peripheral interface and a radio frequency antenna for wireless communication with the upper computer and for transmitting analysis results of the power system network data.

[0010] Preferably, the STM32 microcontroller is of an STM32F767ZI type, and the STM32 microcontroller of the STM32F767ZI type adopts an ARM Cortex-M7 32-bit processor core for further application to running of the classifier.

[0011] Preferably, the data processing device is of a NUCLEO-F767ZI type.

[0012] Preferably, the static random access memory is of an IS61WV102416BLL-10TLI type, and the static random access memory of the IS61WV102416BLL-10TLI type is a 64Mbit external SRAM chip for facilitating quick adjustment according to types and capacities of the network data of the power system.

[0013] Preferably, the communication control device is of a Lora communication module.

[0014] Preferably, the Lora communication module is of a HopeRF RFM95W type.

[0015] Preferably, the radio frequency antenna is of an Antenova M10578-A2 type for facilitating connection with more devices in the edge computing field.

[0016] Beneficial effects: The power network flow classification device based on the STM32 microcontroller has the advantages of low cost and low power consumption, is suitable for long-term running of power network devices, can effectively prolong the service life of the device, has rich peripheral interfaces and flexible software development advantages, and is more suitable for application scenarios of power network flow classification. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a structural schematic view of the device of the utility model.

[0018] Figure 2 The frame principle diagram of the power network flow classification system.

[0019] Figure 3 The power network flow classification process diagram. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0021] The present application will be further described below with reference to specific embodiments.

[0022] Embodiment 1

[0023] This embodiment introduces a power network flow classification device based on an STM32 microcontroller, which comprises a flow data storage device 1, a data processing device 2 and a communication control device 3.

[0024] The data processing device 2 comprises a mainboard, a controller, an Ethernet port, a first serial peripheral interface and a second serial peripheral interface, the controller is connected with the Ethernet port, the first serial peripheral interface and the second serial peripheral interface through a bus, the controller adopts an STM32 microcontroller, is used for running a classifier model, and adopts the classifier model to analyze power system network data.

[0025] The flow data storage device 1 comprises a first serial interface, the first serial interface is connected with the first serial peripheral interface, and the flow data storage device 1 adopts a static random access memory and is used for storing power system network data.

[0026] The communication control device 3 comprises a second serial interface and a radio frequency antenna, the second serial interface is connected with the second serial peripheral interface, the radio frequency antenna performs wireless communication with an upper computer, and is used for transmitting an analysis result of power system network data.

[0027] Further, the model of the STM32 microcontroller adopts an STM32F767ZI, the STM32 microcontroller of the STM32F767ZI model adopts an ARM Cortex-M7 32-bit processor core, and is further suitable for running the classifier.

[0028] Further, the data processing device 2 adopts NUCLEO-F767ZI.

[0029] Further, the static random access memory adopts IS61WV102416BLL-10TLI. The static random access memory of IS61WV102416BLL-10TLI type is a 64Mbit external SRAM chip, which is used to facilitate the rapid adjustment according to the type and capacity of the network data of the power system.

[0030] Further, the communication control device 3 adopts Lora communication module.

[0031] Further, the Lora communication module adopts HopeRF RFM95W.

[0032] Further, the radio frequency antenna adopts Antenova M10578-A2, which is used to facilitate the connection between the edge computing field and more devices.

[0033] Embodiment 2:

[0034] This embodiment introduces a working principle of a power network flow classification device based on STM32 microcontroller, as shown in Figure 2 The power system network device is connected with the Ethernet port of the NUCLEO-F767ZI platform of the device through the Ethernet port. The NUCLEO-F767ZI platform listens to the Ethernet port on the hardware platform through the lwIP protocol stack, obtains the network flow data packet of the power system network device through the Ethernet port, and sends it to the external SRAM of VIS61WV102416BLL-10TLI type through the SPI interface, to provide data for the subsequent flow classification. The network flow data packet includes: flow duration, protocol number, packet length and other information.

[0035] The NUCLEO-F767ZI platform building process is as follows: (1) communication control module peripheral connection, (2) system image burning, (3) starting hardware platform, (4) installing remote desktop, (5) installing python module, (6) installing corresponding classifier model package.

[0036] As shown in Figure 3As shown, the STM32 microcontroller of the STM32F767ZI model of the NUCLEO-F767ZI platform first arranges the collected network flow data into the same data structure as in the training process of the SVM classifier and extracts features, and then inputs the extracted features into the trained SVM classifier to analyze the network flow classification details of the power network. The processor adopts an ARM architecture, has more peripheral resources than an 8-bit single-chip microcomputer, is more cost-effective, and can meet the requirements of the classification system.

[0037] The communication control device integrates components such as a LoRa modem, a radio frequency front end, and an antenna interface, facilitating long-distance, low-power wireless communication.

[0038] The above only describes preferred embodiments of the present application, and it should be pointed out that for ordinary skilled persons in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered within the protection scope of the present application.

Claims

1. A power network traffic classification device based on STM32 microcontroller, characterized in that: Comprise: Flow data storage device, data processing device and communication control device; Wherein, the data processing device, comprising: mainboard, the mainboard is provided with controller, Ethernet port, first serial peripheral interface and second serial peripheral interface, the controller is connected with Ethernet port, first serial peripheral interface and second serial peripheral interface respectively through bus, the controller uses STM32 microcontroller, for running classifier model, uses classifier model to carry out the analysis of power system network data; The flow data storage device, comprising: first serial interface, the first serial interface is connected with first serial peripheral interface, the flow data storage device uses static random access memory, for storing the network data of power system; The communication control device, comprising: second serial interface, radio frequency antenna, the second serial interface is connected with second serial peripheral interface, the radio frequency antenna carries out wireless communication between host computer, for transmitting the analysis result of power system network data.

2. The power network traffic classification device based on STM32 microcontroller according to claim 1, characterized in that: The model of STM32 microcontroller uses STM32F767ZI, the STM32 microcontroller of STM32F767ZI model uses ARM Cortex-M7 32-bit processor kernel, for further suitable for the operation of classifier.

3. The power network traffic classification device based on STM32 microcontroller according to claim 1, characterized in that: The data processing device uses NUCLEO-F767ZI.

4. The power network traffic classification device based on STM32 microcontroller according to claim 1, characterized in that: The model of static random access memory uses IS61WV102416BLL-10TLI, the static random access memory of IS61WV102416BLL-10TLI model is a 64Mbit external SRAM chip, for the network data of power system is convenient according to the type and capacity of fast adjustment.

5. The power network traffic classification device based on STM32 microcontroller according to claim 1, characterized in that: The communication control device uses Lora communication module.

6. The power network traffic classification device based on STM32 microcontroller according to claim 5, characterized in that: The model of Lora communication module uses HopeRF RFM95W.

7. The power network traffic classification device based on STM32 microcontroller according to claim 1, characterized in that: The model of radio frequency antenna uses Antenova M10578-A2, for the convenience of edge computing field and more equipment are connected.

Images